ThinkNEO Control Plane

Official74 toolsLive

by thinkneo-ai · Python

Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.

ai.thinkneo/control-plane (MCP Server)

The ai.thinkneo/control-plane MCP server provides an enterprise AI control plane for governance, guardrails, spend tracking, compliance, and smart routing. It is presented as part of the ThinkNEO Platform and is positioned with a built-in defense layer named ThinkShield. The server is an open MCP server.

🛠️ Key Features

ThinkShield defense layer
Enterprise AI governance
Guardrails
Spend tracking
Compliance
Smart routing

🚀 Use Cases

Applying governance and guardrails to AI workflows
Tracking spend in enterprise settings
Enforcing compliance requirements
Routing AI interactions based on policy

⚡ Developer Benefits

MCP Server built for Model Context Protocol
Includes 74 tools
Listed topics include mcp, model-context-protocol, and agent-to-agent (A2A)
Identified protocol versions include MCP-2024-11-05 and A2A v0.3.0

⚠️ Limitations

Source material does not enumerate specific tool names, inputs/outputs, or configuration options.

Topics

a2a-protocolagent-to-agentai-governanceenterprisefinopsguardrailsmcpmodel-context-protocol

Captured live from the server via tools/list.

thinkneo_check_spend

Check AI spend summary for a workspace, team, or project. Returns real cost breakdown by provider, model, and time period from the ThinkNEO AI gateway.

Parameters3

workspace	string	optional	Workspace name or ID
period	string	optional	Time period: today, this-week, this-month, last-month
group_by	string	optional	Group costs by: provider, model, team, or project

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace name or ID",
      "title": "Workspace",
      "type": "string"
    },
    "period": {
      "default": "this-month",
      "description": "Time period: today, this-week, this-month, last-month",
      "title": "Period",
      "type": "string"
    },
    "group_by": {
      "default": "provider",
      "description": "Group costs by: provider, model, team, or project",
      "title": "Group By",
      "type": "string"
    }
  },
  "title": "thinkneo_check_spendArguments"
}

thinkneo_complete

Run a governed LLM completion through the ThinkNEO AI gateway. The request is authorized, classified, and policy-checked against your workspace governance BEFORE any provider is called — a blocked prompt never reaches the model. Tenant/workspace are derived from your API key.

Parameters5

prompt	string	required	The user prompt to complete
model	string	optional	provider/model, e.g. 'anthropic/claude-haiku-4-5-20251001'
system	any	optional	Optional system instruction
max_tokens	integer	optional	Max output tokens
temperature	number	optional	Sampling temperature

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "description": "The user prompt to complete",
      "title": "Prompt",
      "type": "string"
    },
    "model": {
      "default": "anthropic/claude-haiku-4-5-20251001",
      "description": "provider/model, e.g. 'anthropic/claude-haiku-4-5-20251001'",
      "title": "Model",
      "type": "string"
    },
    "system": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional system instruction",
      "title": "System"
    },
    "max_tokens": {
      "default": 256,
      "description": "Max output tokens",
      "title": "Max Tokens",
      "type": "integer"
    },
    "temperature": {
      "default": 0.7,
      "description": "Sampling temperature",
      "title": "Temperature",
      "type": "number"
    }
  },
  "required": [
    "prompt"
  ],
  "title": "thinkneo_completeArguments"
}

thinkneo_read_memory

Read Claude Code project memory files. Without arguments, returns the MEMORY.md index listing all available memories. With a filename argument, returns the full content of that specific memory file. Use this to access project context, user preferences, feedback, and reference notes persisted across Claude Code sessions.

Parameters1

filename

any

optional

Name of the memory file to read (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Omit to get the MEMORY.md index with all available files.

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Name of the memory file to read (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Omit to get the MEMORY.md index with all available files.",
      "title": "Filename"
    }
  },
  "title": "thinkneo_read_memoryArguments"
}

thinkneo_write_memory

Write or update a Claude Code project memory file (.md). Persists project context, user preferences, feedback, and reference notes across Claude Code sessions. Filename must end in .md with lowercase alphanumeric characters. Path traversal is blocked. Requires authentication.Use this to persist project context, user preferences, feedback, and reference notes across Claude Code sessions. The filename must end in .md and contain only lowercase letters, digits, underscores, and hyphens (e.g. 'user_fabio.md', 'project_new_feature.md'). Path traversal is blocked.

Parameters2

filename	string	required	Name of the memory file to write (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Must end in .md.
content	string	required	Full markdown content to write to the file.

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "description": "Name of the memory file to write (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Must end in .md.",
      "title": "Filename",
      "type": "string"
    },
    "content": {
      "description": "Full markdown content to write to the file.",
      "title": "Content",
      "type": "string"
    }
  },
  "required": [
    "filename",
    "content"
  ],
  "title": "thinkneo_write_memoryArguments"
}

thinkneo_evaluate_guardrail

Evaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider. Returns risk assessment, violations found, and recommendations. Requires authentication.

Parameters3

text	string	required	The prompt or text content to evaluate for policy violations (max 32,000 characters)
workspace	string	required	Workspace whose guardrail policies to apply for this evaluation
guardrail_mode	string	optional	Evaluation mode: 'monitor' (log violations only) or 'enforce' (block the request on violation)

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "description": "The prompt or text content to evaluate for policy violations (max 32,000 characters)",
      "title": "Text",
      "type": "string"
    },
    "workspace": {
      "description": "Workspace whose guardrail policies to apply for this evaluation",
      "title": "Workspace",
      "type": "string"
    },
    "guardrail_mode": {
      "default": "monitor",
      "description": "Evaluation mode: 'monitor' (log violations only) or 'enforce' (block the request on violation)",
      "title": "Guardrail Mode",
      "type": "string"
    }
  },
  "required": [
    "text",
    "workspace"
  ],
  "title": "thinkneo_evaluate_guardrailArguments"
}

thinkneo_check

Free-tier prompt safety check. Analyzes text for prompt injection patterns and PII (credit card numbers, Brazilian CPF, US SSN, email, phone, passwords). Returns a safety assessment with specific warnings. No authentication required.

Parameters1

text

string

required

The text or prompt to check for safety issues (max 50,000 characters)

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "description": "The text or prompt to check for safety issues (max 50,000 characters)",
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "title": "thinkneo_checkArguments"
}

thinkneo_check_policy

Check AI governance policies including model access, budget limits, data controls, and agent governance from the ThinkNEO gateway.

Parameters1

workspace

string

optional

Workspace name or ID

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace name or ID",
      "title": "Workspace",
      "type": "string"
    }
  },
  "title": "thinkneo_check_policyArguments"
}

thinkneo_get_budget_status

Check AI budget status including spend vs limit, forecast, and chargeback data from the ThinkNEO gateway.

Parameters1

workspace

string

optional

Workspace name or ID

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace name or ID",
      "title": "Workspace",
      "type": "string"
    }
  },
  "title": "thinkneo_get_budget_statusArguments"
}

thinkneo_list_alerts

List active alerts for budget, policy, SLA, and security from the ThinkNEO gateway.

Parameters2

workspace	string	optional	Workspace name or ID
severity	string	optional	Filter by severity: critical, high, medium, low, all

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace name or ID",
      "title": "Workspace",
      "type": "string"
    },
    "severity": {
      "default": "all",
      "description": "Filter by severity: critical, high, medium, low, all",
      "title": "Severity",
      "type": "string"
    }
  },
  "title": "thinkneo_list_alertsArguments"
}

thinkneo_get_compliance_status

Get compliance status including framework coverage (EU AI Act, ISO 42001, NIST AI RMF, SOC 2) and governance assessments from the ThinkNEO gateway.

Parameters2

workspace	string	optional	Workspace name or ID
framework	string	optional	Filter by framework: eu-ai-act, iso-42001, nist-ai-rmf, soc2, all

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace name or ID",
      "title": "Workspace",
      "type": "string"
    },
    "framework": {
      "default": "all",
      "description": "Filter by framework: eu-ai-act, iso-42001, nist-ai-rmf, soc2, all",
      "title": "Framework",
      "type": "string"
    }
  },
  "title": "thinkneo_get_compliance_statusArguments"
}

thinkneo_provider_status

Get real-time health and performance status of AI providers routed through the ThinkNEO gateway. Shows latency, error rates, and availability. No authentication required.

Parameters2

provider	any	optional	Specific provider to check: openai, anthropic, google, mistral, xai, cohere, or together. Omit to get status for all providers.
workspace	any	optional	Workspace context for provider routing configuration (optional)

Raw schema

{
  "type": "object",
  "properties": {
    "provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Specific provider to check: openai, anthropic, google, mistral, xai, cohere, or together. Omit to get status for all providers.",
      "title": "Provider"
    },
    "workspace": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Workspace context for provider routing configuration (optional)",
      "title": "Workspace"
    }
  },
  "title": "thinkneo_provider_statusArguments"
}

thinkneo_schedule_demo

Schedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required.

Parameters7

contact_name	string	required	Full name of the person requesting the demo
company	string	required	Company or organization name
email	string	required	Business email address to receive follow-up from the ThinkNEO team
role	any	optional	Contact's role: cto, cfo, security, engineering, or other
interest	any	optional	Primary area of interest: guardrails, finops, observability, governance, or full platform
preferred_dates	any	optional	Preferred meeting dates, times, and timezone (e.g., 'Tuesdays or Thursdays, 9-11am EST')
context	any	optional	Additional context such as current AI providers used, request volume, or specific use case

Raw schema

{
  "type": "object",
  "properties": {
    "contact_name": {
      "description": "Full name of the person requesting the demo",
      "title": "Contact Name",
      "type": "string"
    },
    "company": {
      "description": "Company or organization name",
      "title": "Company",
      "type": "string"
    },
    "email": {
      "description": "Business email address to receive follow-up from the ThinkNEO team",
      "title": "Email",
      "type": "string"
    },
    "role": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Contact's role: cto, cfo, security, engineering, or other",
      "title": "Role"
    },
    "interest": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Primary area of interest: guardrails, finops, observability, governance, or full platform",
      "title": "Interest"
    },
    "preferred_dates": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Preferred meeting dates, times, and timezone (e.g., 'Tuesdays or Thursdays, 9-11am EST')",
      "title": "Preferred Dates"
    },
    "context": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Additional context such as current AI providers used, request volume, or specific use case",
      "title": "Context"
    }
  },
  "required": [
    "contact_name",
    "company",
    "email"
  ],
  "title": "thinkneo_schedule_demoArguments"
}

thinkneo_usage

Returns usage statistics for your ThinkNEO API key. Shows calls today, this week, this month, monthly limit, remaining calls, top tools used, estimated cost, and current tier. Works without authentication (returns general info).

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "title": "thinkneo_usageArguments"
}

thinkneo_route_model

AI Smart Router — find the cheapest model that meets your quality threshold. Specify your task type and quality requirements, and ThinkNEO will recommend the optimal model with estimated cost and savings vs premium models. Supports 17+ models across Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Alibaba, Cohere, and xAI. Requires authentication.

Parameters7

task_type	string	required	The type of AI task: summarization, classification, code_generation, chat, analysis, translation, or embedding
quality_threshold	integer	optional	Minimum quality score required (0-100). Default 85 = enterprise-grade.
max_latency_ms	any	optional	Maximum acceptable latency in milliseconds. Omit for no limit.
budget_per_request	any	optional	Maximum budget per request in USD. Omit for no limit.
preferred_providers	any	optional	Comma-separated list of preferred providers (e.g., 'openai,anthropic'). These will be prioritized at similar cost.
estimated_tokens	integer	optional	Estimated total tokens for the request (input + output). Default 1000.
text_sample	any	optional	Optional sample text for better routing. Helps estimate token count and task complexity. Max 500 characters.

Raw schema

{
  "type": "object",
  "properties": {
    "task_type": {
      "description": "The type of AI task: summarization, classification, code_generation, chat, analysis, translation, or embedding",
      "title": "Task Type",
      "type": "string"
    },
    "quality_threshold": {
      "default": 85,
      "description": "Minimum quality score required (0-100). Default 85 = enterprise-grade.",
      "title": "Quality Threshold",
      "type": "integer"
    },
    "max_latency_ms": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Maximum acceptable latency in milliseconds. Omit for no limit.",
      "title": "Max Latency Ms"
    },
    "budget_per_request": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Maximum budget per request in USD. Omit for no limit.",
      "title": "Budget Per Request"
    },
    "preferred_providers": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Comma-separated list of preferred providers (e.g., 'openai,anthropic'). These will be prioritized at similar cost.",
      "title": "Preferred Providers"
    },
    "estimated_tokens": {
      "default": 1000,
      "description": "Estimated total tokens for the request (input + output). Default 1000.",
      "title": "Estimated Tokens",
      "type": "integer"
    },
    "text_sample": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional sample text for better routing. Helps estimate token count and task complexity. Max 500 characters.",
      "title": "Text Sample"
    }
  },
  "required": [
    "task_type"
  ],
  "title": "thinkneo_route_modelArguments"
}

thinkneo_get_savings_report

Get your AI cost savings report. Shows total requests routed, original cost (what you'd have paid with premium models), actual cost, total savings, savings percentage, breakdown by task type, and model distribution. Requires authentication.

Parameters1

period

string

optional

Report period: '7d' (7 days), '30d' (30 days), or '90d' (90 days)

Raw schema

{
  "type": "object",
  "properties": {
    "period": {
      "default": "30d",
      "description": "Report period: '7d' (7 days), '30d' (30 days), or '90d' (90 days)",
      "title": "Period",
      "type": "string"
    }
  },
  "title": "thinkneo_get_savings_reportArguments"
}

thinkneo_simulate_savings

Simulate how much your organization would save on AI costs using ThinkNEO Smart Router. Enter your current monthly AI spend and primary model, and see estimated monthly and annual savings with a recommended model mix. No authentication required — try it now!

Parameters3

monthly_ai_spend	number	required	Your current monthly AI API spend in USD (e.g., 5000.00)
primary_model	string	optional	Your primary model: 'gpt-4o', 'claude-opus-4', 'claude-sonnet-4', 'gpt-4.1', or 'gemini-2.5-pro'
task_distribution	any	optional	JSON string of task distribution, e.g., '{"chat": 0.3, "summarization": 0.2, "code_generation": 0.2, "classification": 0.15, "analysis": 0.1, "translation": 0.05}'. Values should sum to ~1.0. Omit for default enterprise distribution.

Raw schema

{
  "type": "object",
  "properties": {
    "monthly_ai_spend": {
      "description": "Your current monthly AI API spend in USD (e.g., 5000.00)",
      "title": "Monthly Ai Spend",
      "type": "number"
    },
    "primary_model": {
      "default": "gpt-4o",
      "description": "Your primary model: 'gpt-4o', 'claude-opus-4', 'claude-sonnet-4', 'gpt-4.1', or 'gemini-2.5-pro'",
      "title": "Primary Model",
      "type": "string"
    },
    "task_distribution": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "JSON string of task distribution, e.g., '{\"chat\": 0.3, \"summarization\": 0.2, \"code_generation\": 0.2, \"classification\": 0.15, \"analysis\": 0.1, \"translation\": 0.05}'. Values should sum to ~1.0. Omit for default enterprise distribution.",
      "title": "Task Distribution"
    }
  },
  "required": [
    "monthly_ai_spend"
  ],
  "title": "thinkneo_simulate_savingsArguments"
}

thinkneo_evaluate_trust_score

Evaluate your organization AI Trust Score (0-100) across 10 dimensions: Guardrails, PII Protection, Injection Defense, Audit Trail, Compliance, Model Governance, Cost Controls, Outcome Validation, Observability, and Smart Routing. Returns a score, detailed breakdown, badge level (Platinum/Gold/Silver/Bronze/Unrated), and actionable recommendations. Score is valid for 30 days. Generates a public badge URL for embedding in websites and documentation. Part of the 'From Prompt to Proof' framework. Requires authentication.

Parameters1

org_name

string

required

Organization name for the trust score badge (e.g., 'Acme Corp')

Raw schema

{
  "type": "object",
  "properties": {
    "org_name": {
      "description": "Organization name for the trust score badge (e.g., 'Acme Corp')",
      "title": "Org Name",
      "type": "string"
    }
  },
  "required": [
    "org_name"
  ],
  "title": "thinkneo_evaluate_trust_scoreArguments"
}

thinkneo_get_trust_badge

Get a public AI Trust Score badge by report token. Returns the organization name, score, badge level, and validity period. Use the badge URL to embed the trust badge in websites and documentation. No authentication required.

Parameters1

report_token

string

required

The report token from a trust score evaluation (URL-safe string)

Raw schema

{
  "type": "object",
  "properties": {
    "report_token": {
      "description": "The report token from a trust score evaluation (URL-safe string)",
      "title": "Report Token",
      "type": "string"
    }
  },
  "required": [
    "report_token"
  ],
  "title": "thinkneo_get_trust_badgeArguments"
}

thinkneo_registry_search

Search the ThinkNEO MCP Marketplace — the npm for MCP tools. Discover MCP servers and tools by keyword, category, rating, or verified status. Returns name, description, tools count, rating, downloads, and verified badge. No authentication required.

Parameters5

query	string	optional	Search query — matches name, description, tags, and tool names
category	any	optional	Filter by category: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other
min_rating	any	optional	Minimum average rating (1.0-5.0)
verified_only	boolean	optional	If true, return only verified packages
limit	integer	optional	Max results to return (1-100, default 20)

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "default": "",
      "description": "Search query — matches name, description, tags, and tool names",
      "title": "Query",
      "type": "string"
    },
    "category": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by category: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other",
      "title": "Category"
    },
    "min_rating": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Minimum average rating (1.0-5.0)",
      "title": "Min Rating"
    },
    "verified_only": {
      "default": false,
      "description": "If true, return only verified packages",
      "title": "Verified Only",
      "type": "boolean"
    },
    "limit": {
      "default": 20,
      "description": "Max results to return (1-100, default 20)",
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "thinkneo_registry_searchArguments"
}

thinkneo_registry_get

Get full details for an MCP server package from the ThinkNEO Marketplace. Returns readme, full tools list, version history, reviews, security score, and installation instructions. No authentication required.

Parameters1

name

string

required

Package name (e.g. 'thinkneo-control-plane', 'filesystem', 'github')

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Package name (e.g. 'thinkneo-control-plane', 'filesystem', 'github')",
      "title": "Name",
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "title": "thinkneo_registry_getArguments"
}

thinkneo_registry_publish

Publish an MCP server to the ThinkNEO Marketplace. Validates the endpoint by calling initialize and tools/list, runs automated security scan for secrets and injection patterns, computes a security score (0-100), and stores the entry with version history. Validates the endpoint (calls initialize + tools/list), runs security scan (secrets detection, injection patterns), and stores the entry. Authentication required.

Parameters10

name	string	required	Package name (lowercase, hyphens allowed, e.g. 'my-mcp-server')
display_name	string	required	Human-readable display name
description	string	required	Short description of what this MCP server does (max 500 chars)
endpoint_url	string	required	MCP server endpoint URL (e.g. https://my-server.com/mcp)
transport	string	optional	Transport type: streamable-http, sse, or stdio
categories	any	optional	Categories: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other
tags	any	optional	Tags for discoverability (e.g. ['ai', 'governance', 'security'])
repo_url	string	optional	Source code repository URL
license	string	optional	License (e.g. MIT, Apache-2.0)
readme	string	optional	Full readme/documentation in markdown

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Package name (lowercase, hyphens allowed, e.g. 'my-mcp-server')",
      "title": "Name",
      "type": "string"
    },
    "display_name": {
      "description": "Human-readable display name",
      "title": "Display Name",
      "type": "string"
    },
    "description": {
      "description": "Short description of what this MCP server does (max 500 chars)",
      "title": "Description",
      "type": "string"
    },
    "endpoint_url": {
      "description": "MCP server endpoint URL (e.g. https://my-server.com/mcp)",
      "title": "Endpoint Url",
      "type": "string"
    },
    "transport": {
      "default": "streamable-http",
      "description": "Transport type: streamable-http, sse, or stdio",
      "title": "Transport",
      "type": "string"
    },
    "categories": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Categories: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other",
      "title": "Categories"
    },
    "tags": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Tags for discoverability (e.g. ['ai', 'governance', 'security'])",
      "title": "Tags"
    },
    "repo_url": {
      "default": "",
      "description": "Source code repository URL",
      "title": "Repo Url",
      "type": "string"
    },
    "license": {
      "default": "MIT",
      "description": "License (e.g. MIT, Apache-2.0)",
      "title": "License",
      "type": "string"
    },
    "readme": {
      "default": "",
      "description": "Full readme/documentation in markdown",
      "title": "Readme",
      "type": "string"
    }
  },
  "required": [
    "name",
    "display_name",
    "description",
    "endpoint_url"
  ],
  "title": "thinkneo_registry_publishArguments"
}

thinkneo_registry_review

Rate and review an MCP server in the ThinkNEO Marketplace. One review per user per package (updates on repeat). Rating from 1 (poor) to 5 (excellent) with optional comment. Reviews affect the package average rating shown in search results. One review per user per package (updates on repeat). Authentication required.

Parameters3

name	string	required	Package name to review
rating	integer	required	Rating from 1 (poor) to 5 (excellent)
comment	string	optional	Review comment (max 2000 chars)

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Package name to review",
      "title": "Name",
      "type": "string"
    },
    "rating": {
      "description": "Rating from 1 (poor) to 5 (excellent)",
      "title": "Rating",
      "type": "integer"
    },
    "comment": {
      "default": "",
      "description": "Review comment (max 2000 chars)",
      "title": "Comment",
      "type": "string"
    }
  },
  "required": [
    "name",
    "rating"
  ],
  "title": "thinkneo_registry_reviewArguments"
}

thinkneo_registry_install

Get installation config for an MCP server from the ThinkNEO Marketplace. Returns ready-to-use JSON config for Claude Desktop, Cursor, Windsurf, or custom clients. Tracks the download. No authentication required.

Parameters2

name	string	required	Package name to install (e.g. 'thinkneo-control-plane')
client_type	string	optional	Your MCP client: claude-desktop, cursor, windsurf, or custom

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Package name to install (e.g. 'thinkneo-control-plane')",
      "title": "Name",
      "type": "string"
    },
    "client_type": {
      "default": "claude-desktop",
      "description": "Your MCP client: claude-desktop, cursor, windsurf, or custom",
      "title": "Client Type",
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "title": "thinkneo_registry_installArguments"
}

thinkneo_bridge_mcp_to_a2a

Bridge MCP tool registry to A2A format. Shows tool-to-skill mappings.

Parameters1

tool_name

string

optional

MCP tool name to bridge

Raw schema

{
  "type": "object",
  "properties": {
    "tool_name": {
      "default": "",
      "description": "MCP tool name to bridge",
      "title": "Tool Name",
      "type": "string"
    }
  },
  "title": "thinkneo_bridge_mcp_to_a2aArguments"
}

thinkneo_bridge_a2a_to_mcp

Bridge A2A agents to MCP tool format.

Parameters1

agent_name

string

optional

A2A agent name to map

Raw schema

{
  "type": "object",
  "properties": {
    "agent_name": {
      "default": "",
      "description": "A2A agent name to map",
      "title": "Agent Name",
      "type": "string"
    }
  },
  "title": "thinkneo_bridge_a2a_to_mcpArguments"
}

thinkneo_bridge_generate_agent_card

Generate an A2A Agent Card from registry data.

Parameters1

agent_id

string

required

Agent ID from registry

Raw schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "description": "Agent ID from registry",
      "title": "Agent Id",
      "type": "string"
    }
  },
  "required": [
    "agent_id"
  ],
  "title": "thinkneo_bridge_generate_agent_cardArguments"
}

thinkneo_bridge_list_mappings

List all MCP <-> A2A bridge mappings for a tenant.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "title": "thinkneo_bridge_list_mappingsArguments"
}

thinkneo_start_trace

Start a new agent observability trace. Creates a session that tracks all tool calls, model calls, decisions, and errors for an AI agent run. Returns a session_id to use with thinkneo_log_event and thinkneo_end_trace. Requires authentication.

Parameters3

agent_name	string	required	Name of the agent being traced (e.g., 'marketing-agent', 'support-bot')
agent_type	string	optional	Type of agent: 'assistant', 'autonomous', 'workflow', 'pipeline', or 'generic'
metadata	any	optional	Optional dict with additional context (e.g., {"task": "email-draft", "user_id": "u123"})

Raw schema

{
  "type": "object",
  "properties": {
    "agent_name": {
      "description": "Name of the agent being traced (e.g., 'marketing-agent', 'support-bot')",
      "title": "Agent Name",
      "type": "string"
    },
    "agent_type": {
      "default": "generic",
      "description": "Type of agent: 'assistant', 'autonomous', 'workflow', 'pipeline', or 'generic'",
      "title": "Agent Type",
      "type": "string"
    },
    "metadata": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional dict with additional context (e.g., {\"task\": \"email-draft\", \"user_id\": \"u123\"})",
      "title": "Metadata"
    }
  },
  "required": [
    "agent_name"
  ],
  "title": "thinkneo_start_traceArguments"
}

thinkneo_log_event

Log an event within an active agent trace. Supports event types: tool_call, model_call, decision, error, pii_access, guardrail_triggered. Returns event_id and running session cost. Requires authentication.

Parameters9

session_id	string	required	Session ID from thinkneo_start_trace
event_type	string	required	Event type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'
tool_name	any	optional	Name of the tool called (for tool_call events)
model_name	any	optional	Model used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')
input_summary	any	optional	Brief summary of the input (max 500 chars, truncated if longer)
output_summary	any	optional	Brief summary of the output (max 500 chars, truncated if longer)
cost	number	optional	Estimated cost in USD for this event (e.g., 0.003 for an API call)
latency_ms	integer	optional	Latency in milliseconds for this event
metadata	any	optional	Optional dict with additional event context

Raw schema

{
  "type": "object",
  "properties": {
    "session_id": {
      "description": "Session ID from thinkneo_start_trace",
      "title": "Session Id",
      "type": "string"
    },
    "event_type": {
      "description": "Event type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'",
      "title": "Event Type",
      "type": "string"
    },
    "tool_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Name of the tool called (for tool_call events)",
      "title": "Tool Name"
    },
    "model_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Model used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')",
      "title": "Model Name"
    },
    "input_summary": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Brief summary of the input (max 500 chars, truncated if longer)",
      "title": "Input Summary"
    },
    "output_summary": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Brief summary of the output (max 500 chars, truncated if longer)",
      "title": "Output Summary"
    },
    "cost": {
      "default": 0,
      "description": "Estimated cost in USD for this event (e.g., 0.003 for an API call)",
      "title": "Cost",
      "type": "number"
    },
    "latency_ms": {
      "default": 0,
      "description": "Latency in milliseconds for this event",
      "title": "Latency Ms",
      "type": "integer"
    },
    "metadata": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional dict with additional event context",
      "title": "Metadata"
    }
  },
  "required": [
    "session_id",
    "event_type"
  ],
  "title": "thinkneo_log_eventArguments"
}

thinkneo_end_trace

End an active agent trace and get the session summary. Returns total cost, duration, tool/model call counts, and event count. Triggers post-session anomaly detection (cost spikes, error rate). Requires authentication.

Parameters2

session_id	string	required	Session ID from thinkneo_start_trace
status	string	optional	Final session status: 'success', 'failure', or 'timeout'

Raw schema

{
  "type": "object",
  "properties": {
    "session_id": {
      "description": "Session ID from thinkneo_start_trace",
      "title": "Session Id",
      "type": "string"
    },
    "status": {
      "default": "success",
      "description": "Final session status: 'success', 'failure', or 'timeout'",
      "title": "Status",
      "type": "string"
    }
  },
  "required": [
    "session_id"
  ],
  "title": "thinkneo_end_traceArguments"
}

thinkneo_get_trace

Retrieve the full trace for an agent session. Returns the complete timeline of events (tool calls, model calls, decisions, errors), session metadata, total cost, duration, and any alerts triggered. Requires authentication.

Parameters1

session_id

string

required

Session ID to retrieve the trace for

Raw schema

{
  "type": "object",
  "properties": {
    "session_id": {
      "description": "Session ID to retrieve the trace for",
      "title": "Session Id",
      "type": "string"
    }
  },
  "required": [
    "session_id"
  ],
  "title": "thinkneo_get_traceArguments"
}

thinkneo_get_observability_dashboard

Get the agent observability dashboard — aggregated metrics for your AI agents. Includes total sessions, events, cost, error rate, latency, top agents, top tools, active alerts, and cost trend over time. Like Datadog, but for AI agents. Requires authentication.

Parameters1

period

string

optional

Time period: '1h', '24h', '7d', or '30d'

Raw schema

{
  "type": "object",
  "properties": {
    "period": {
      "default": "24h",
      "description": "Time period: '1h', '24h', '7d', or '30d'",
      "title": "Period",
      "type": "string"
    }
  },
  "title": "thinkneo_get_observability_dashboardArguments"
}

thinkneo_set_baseline

Define the pre-AI cost baseline for a business process. Example: 'customer_support_ticket costs $12 per ticket and takes 15 minutes without AI'. This baseline is used to calculate ROI when agents handle the same process. Call this once per process to establish the comparison point.

Parameters6

process_name	string	required	Name of the business process, e.g. 'customer_support_ticket', 'loan_review', 'content_moderation'
cost_per_unit_usd	number	required	Pre-AI cost per unit in USD, e.g. 12.00 for a $12 support ticket
unit_label	string	optional	What one unit represents, e.g. 'ticket', 'review', 'decision', 'document'
avg_duration_minutes	any	optional	Average time in minutes for one unit without AI, e.g. 15
workspace	string	optional	Workspace identifier
notes	any	optional	Additional context about this baseline

Raw schema

{
  "type": "object",
  "properties": {
    "process_name": {
      "description": "Name of the business process, e.g. 'customer_support_ticket', 'loan_review', 'content_moderation'",
      "title": "Process Name",
      "type": "string"
    },
    "cost_per_unit_usd": {
      "description": "Pre-AI cost per unit in USD, e.g. 12.00 for a $12 support ticket",
      "title": "Cost Per Unit Usd",
      "type": "number"
    },
    "unit_label": {
      "default": "unit",
      "description": "What one unit represents, e.g. 'ticket', 'review', 'decision', 'document'",
      "title": "Unit Label",
      "type": "string"
    },
    "avg_duration_minutes": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Average time in minutes for one unit without AI, e.g. 15",
      "title": "Avg Duration Minutes"
    },
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "notes": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Additional context about this baseline",
      "title": "Notes"
    }
  },
  "required": [
    "process_name",
    "cost_per_unit_usd"
  ],
  "title": "thinkneo_set_baselineArguments"
}

thinkneo_log_decision

Log a business decision made by an AI agent. Tracks the AI cost and the business value generated. If a baseline exists for the process, value is auto-calculated from the baseline cost. Example: agent 'support-bot' resolved a 'customer_support_ticket' at $0.03 AI cost, replacing a $12 human-handled ticket. ROI: 400:1.

Parameters9

agent_name	string	required	Name of the AI agent that made the decision, e.g. 'support-bot', 'loan-reviewer'
decision_type	string	required	Type of decision, e.g. 'ticket_resolved', 'loan_approved', 'content_reviewed'
ai_cost_usd	number	optional	Actual AI cost for this decision in USD, e.g. 0.03
process_name	any	optional	Links to a baseline process for auto ROI calculation
value_generated_usd	any	optional	Explicit business value in USD. If omitted and process_name has a baseline, auto-calculated.
outcome	string	optional	Result: 'success', 'escalated', 'rejected', 'error'
confidence	any	optional	Confidence score 0.0-1.0
workspace	string	optional	Workspace identifier
metadata	any	optional	JSON string with additional context

Raw schema

{
  "type": "object",
  "properties": {
    "agent_name": {
      "description": "Name of the AI agent that made the decision, e.g. 'support-bot', 'loan-reviewer'",
      "title": "Agent Name",
      "type": "string"
    },
    "decision_type": {
      "description": "Type of decision, e.g. 'ticket_resolved', 'loan_approved', 'content_reviewed'",
      "title": "Decision Type",
      "type": "string"
    },
    "ai_cost_usd": {
      "default": 0,
      "description": "Actual AI cost for this decision in USD, e.g. 0.03",
      "title": "Ai Cost Usd",
      "type": "number"
    },
    "process_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Links to a baseline process for auto ROI calculation",
      "title": "Process Name"
    },
    "value_generated_usd": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Explicit business value in USD. If omitted and process_name has a baseline, auto-calculated.",
      "title": "Value Generated Usd"
    },
    "outcome": {
      "default": "success",
      "description": "Result: 'success', 'escalated', 'rejected', 'error'",
      "title": "Outcome",
      "type": "string"
    },
    "confidence": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Confidence score 0.0-1.0",
      "title": "Confidence"
    },
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "metadata": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "JSON string with additional context",
      "title": "Metadata"
    }
  },
  "required": [
    "agent_name",
    "decision_type"
  ],
  "title": "thinkneo_log_decisionArguments"
}

thinkneo_log_risk_avoidance

Log a risk event that was blocked or avoided by the governance layer. Quantifies the estimated dollar impact of the avoided risk. Examples: PII leak blocked (est. $50K GDPR fine), prompt injection prevented, policy violation caught before production. If estimated_impact_usd is not provided, a default is calculated from severity.

Parameters6

risk_type	string	required	Type: 'pii_leak', 'injection_blocked', 'policy_violation', 'spend_limit', 'compliance_breach', 'data_exfiltration'
severity	string	optional	Severity level: 'low', 'medium', 'high', 'critical'
estimated_impact_usd	any	optional	Estimated cost if this risk had materialized in USD
agent_name	any	optional	Agent involved, if applicable
description	any	optional	Brief description of what was blocked
workspace	string	optional	Workspace identifier

Raw schema

{
  "type": "object",
  "properties": {
    "risk_type": {
      "description": "Type: 'pii_leak', 'injection_blocked', 'policy_violation', 'spend_limit', 'compliance_breach', 'data_exfiltration'",
      "title": "Risk Type",
      "type": "string"
    },
    "severity": {
      "default": "medium",
      "description": "Severity level: 'low', 'medium', 'high', 'critical'",
      "title": "Severity",
      "type": "string"
    },
    "estimated_impact_usd": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Estimated cost if this risk had materialized in USD",
      "title": "Estimated Impact Usd"
    },
    "agent_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Agent involved, if applicable",
      "title": "Agent Name"
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Brief description of what was blocked",
      "title": "Description"
    },
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    }
  },
  "required": [
    "risk_type"
  ],
  "title": "thinkneo_log_risk_avoidanceArguments"
}

thinkneo_decision_cost

Analyze cost-per-decision for AI agents. Shows the actual AI cost for each decision, compared to the pre-AI baseline. Answers: 'How much does each AI decision cost?' and 'How does it compare to doing it without AI?'

Parameters4

workspace	string	optional	Workspace identifier
agent_name	any	optional	Filter by specific agent
process_name	any	optional	Filter by specific process
period	string	optional	Time period: 'today', 'this-week', 'this-month', 'all'

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "agent_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by specific agent",
      "title": "Agent Name"
    },
    "process_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by specific process",
      "title": "Process Name"
    },
    "period": {
      "default": "this-month",
      "description": "Time period: 'today', 'this-week', 'this-month', 'all'",
      "title": "Period",
      "type": "string"
    }
  },
  "title": "thinkneo_decision_costArguments"
}

thinkneo_agent_roi

Calculate ROI per AI agent. Shows value generated vs AI cost consumed, with daily trend, success rate, and comparison to pre-AI baseline. Answers: 'Is this agent generating or consuming value?' and 'What's the ROI trend?'

Parameters3

workspace	string	optional	Workspace identifier
agent_name	any	optional	Specific agent to analyze. If omitted, returns all agents.
days	integer	optional	Number of days to analyze

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "agent_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Specific agent to analyze. If omitted, returns all agents.",
      "title": "Agent Name"
    },
    "days": {
      "default": 30,
      "description": "Number of days to analyze",
      "title": "Days",
      "type": "integer"
    }
  },
  "title": "thinkneo_agent_roiArguments"
}

thinkneo_business_impact

Executive business impact dashboard. Returns a single view of: total value generated by AI agents, total AI cost, net ROI, risk avoided in dollars, cost per decision, top performing agents, and risk event summary. This is the report a CxO needs to justify AI investment.

Parameters2

workspace	string	optional	Workspace identifier
period	string	optional	Time period: 'this-week', 'this-month', 'this-quarter', 'all'

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "period": {
      "default": "this-month",
      "description": "Time period: 'this-week', 'this-month', 'this-quarter', 'all'",
      "title": "Period",
      "type": "string"
    }
  },
  "title": "thinkneo_business_impactArguments"
}

thinkneo_a2a_log

Retrieve A2A (agent-to-agent) interaction logs from the live gateway. Shows which agents called which, actions performed, costs, and outcomes.

Parameters2

workspace	string	optional	Workspace identifier
limit	integer	optional	Max events to return

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "limit": {
      "default": 50,
      "description": "Max events to return",
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "thinkneo_a2a_logArguments"
}

thinkneo_a2a_policy

Retrieve A2A interaction policies from the live gateway. Shows allowed actions, rate limits, cost caps, and approval requirements.

Parameters1

workspace

string

optional

Workspace identifier

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    }
  },
  "title": "thinkneo_a2a_policyArguments"
}

thinkneo_a2a_flow

Visualize agent-to-agent communication flow. Shows registered agents, their approval status, and interaction patterns from the live gateway.

Parameters1

workspace

string

optional

Workspace identifier

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    }
  },
  "title": "thinkneo_a2a_flowArguments"
}

thinkneo_a2a_audit

Retrieve immutable audit trail for A2A interactions with hash verification. Each event is cryptographically chained for tamper detection.

Parameters2

workspace	string	optional	Workspace identifier
trace_id	any	optional	Filter by trace ID

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "trace_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by trace ID",
      "title": "Trace Id"
    }
  },
  "title": "thinkneo_a2a_auditArguments"
}

thinkneo_detect_waste

Detect waste and inefficiency in AI operations. Analyzes agent performance, A2A communication overhead, error costs, unused capacity, and cost outliers. Returns specific actionable findings like 'you are losing $3,200/month on error retries' or 'this flow is 5x more expensive than your best-performing flow'. This is the diagnostic tool that creates the buying trigger.

Parameters2

workspace	string	optional	Workspace identifier
days	integer	optional	Analysis window in days

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "days": {
      "default": 30,
      "description": "Analysis window in days",
      "title": "Days",
      "type": "integer"
    }
  },
  "title": "thinkneo_detect_wasteArguments"
}

thinkneo_register_claim

Register an action claim from an AI agent. The agent declares it performed an action (e.g., sent an email, created a PR, wrote a file) and ThinkNEO will verify it actually happened. Returns a claim_id for tracking. Part of the Outcome Validation Loop — 'From Prompt to Proof'. Requires authentication.

Parameters7

action	string	required	Type of action claimed: 'email_sent', 'http_request', 'file_written', 'db_insert', 'pr_created', 'payment_processed', 'message_sent', 'api_call', 'task_completed', 'data_exported', 'notification_sent', 'custom'
target	string	required	Target of the action — what was acted upon. Examples: 'user@example.com' (email), 'https://api.example.com/endpoint' (http), '/opt/data/report.pdf' (file), 'usage_log' (db table)
evidence_type	string	required	How to verify the claim: 'http_status' (check URL response), 'file_exists' (check file path), 'db_row_exists' (check database row), 'webhook' (wait for callback), 'smtp_delivery' (check email delivery), 'manual' (flag for human review)
agent_name	any	optional	Name of the agent making the claim (e.g., 'marketing-agent')
session_id	any	optional	Optional observability session_id to link this claim to a trace
metadata	any	optional	Optional verification context. For http_status: {expected_status: 200, method: 'GET'}. For file_exists: {expected_hash: 'sha256...'}. For db_row_exists: {where_column: 'id', where_value: '123'}.
ttl_hours	integer	optional	Hours until claim expires if not verified (default 24, max 168)

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "description": "Type of action claimed: 'email_sent', 'http_request', 'file_written', 'db_insert', 'pr_created', 'payment_processed', 'message_sent', 'api_call', 'task_completed', 'data_exported', 'notification_sent', 'custom'",
      "title": "Action",
      "type": "string"
    },
    "target": {
      "description": "Target of the action — what was acted upon. Examples: 'user@example.com' (email), 'https://api.example.com/endpoint' (http), '/opt/data/report.pdf' (file), 'usage_log' (db table)",
      "title": "Target",
      "type": "string"
    },
    "evidence_type": {
      "description": "How to verify the claim: 'http_status' (check URL response), 'file_exists' (check file path), 'db_row_exists' (check database row), 'webhook' (wait for callback), 'smtp_delivery' (check email delivery), 'manual' (flag for human review)",
      "title": "Evidence Type",
      "type": "string"
    },
    "agent_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Name of the agent making the claim (e.g., 'marketing-agent')",
      "title": "Agent Name"
    },
    "session_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional observability session_id to link this claim to a trace",
      "title": "Session Id"
    },
    "metadata": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional verification context. For http_status: {expected_status: 200, method: 'GET'}. For file_exists: {expected_hash: 'sha256...'}. For db_row_exists: {where_column: 'id', where_value: '123'}.",
      "title": "Metadata"
    },
    "ttl_hours": {
      "default": 24,
      "description": "Hours until claim expires if not verified (default 24, max 168)",
      "title": "Ttl Hours",
      "type": "integer"
    }
  },
  "required": [
    "action",
    "target",
    "evidence_type"
  ],
  "title": "thinkneo_register_claimArguments"
}

thinkneo_verify_claim

Trigger verification of a registered action claim. Runs the appropriate verification adapter (HTTP check, file check, database check, etc.) and returns the result with evidence. If already verified, returns cached result (use force=true to re-verify). Part of the Outcome Validation Loop — 'From Prompt to Proof'. Requires authentication.

Parameters2

claim_id	string	required	UUID of the claim to verify (from thinkneo_register_claim)
force	boolean	optional	Force re-verification even if already verified/failed

Raw schema

{
  "type": "object",
  "properties": {
    "claim_id": {
      "description": "UUID of the claim to verify (from thinkneo_register_claim)",
      "title": "Claim Id",
      "type": "string"
    },
    "force": {
      "default": false,
      "description": "Force re-verification even if already verified/failed",
      "title": "Force",
      "type": "boolean"
    }
  },
  "required": [
    "claim_id"
  ],
  "title": "thinkneo_verify_claimArguments"
}

thinkneo_get_proof

Retrieve the immutable proof record for a verified claim. Includes the original claim, verification evidence, verifier identity, and a SHA-256 proof hash for tamper detection. This is the 'proof' in 'From Prompt to Proof'. Requires authentication.

Parameters1

claim_id

string

required

UUID of the claim to get proof for

Raw schema

{
  "type": "object",
  "properties": {
    "claim_id": {
      "description": "UUID of the claim to get proof for",
      "title": "Claim Id",
      "type": "string"
    }
  },
  "required": [
    "claim_id"
  ],
  "title": "thinkneo_get_proofArguments"
}

thinkneo_verification_dashboard

Aggregated outcome verification metrics — verification rates, failure patterns, agent reliability rankings, and daily trends. Shows how reliably your AI agents are delivering verified outcomes. 'Datadog for AI outcomes'. Requires authentication.

Parameters1

period

string

optional

Time period: '24h', '7d', or '30d'

Raw schema

{
  "type": "object",
  "properties": {
    "period": {
      "default": "7d",
      "description": "Time period: '24h', '7d', or '30d'",
      "title": "Period",
      "type": "string"
    }
  },
  "title": "thinkneo_verification_dashboardArguments"
}

thinkneo_benchmark_report

View the outcome benchmark matrix — real quality scores per provider/model/task_type based on verified outcomes, not static estimates. Shows verification rates, sample counts, and rankings. Requires authentication.

Parameters1

task_type

any

optional

Filter by task type: 'summarization', 'code_generation', 'classification', 'translation', etc. Leave empty for all.

Raw schema

{
  "type": "object",
  "properties": {
    "task_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by task type: 'summarization', 'code_generation', 'classification', 'translation', etc. Leave empty for all.",
      "title": "Task Type"
    }
  },
  "title": "thinkneo_benchmark_reportArguments"
}

thinkneo_benchmark_compare

Compare providers side-by-side for a specific task type. Shows quality scores, verification rates, and rankings based on real outcomes. Requires authentication.

Parameters2

task_type	string	required	Task type to compare: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'
providers	any	optional	Optional list of providers to compare (e.g., ['anthropic', 'openai']). Leave empty for all.

Raw schema

{
  "type": "object",
  "properties": {
    "task_type": {
      "description": "Task type to compare: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'",
      "title": "Task Type",
      "type": "string"
    },
    "providers": {
      "anyOf": [
        {
          "items": {},
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional list of providers to compare (e.g., ['anthropic', 'openai']). Leave empty for all.",
      "title": "Providers"
    }
  },
  "required": [
    "task_type"
  ],
  "title": "thinkneo_benchmark_compareArguments"
}

thinkneo_router_explain

Explain why the Smart Router would choose a specific model for a task type. Shows both benchmark-based (real outcomes) and static quality estimates, and explains the reasoning behind the recommendation. Requires authentication.

Parameters2

task_type	string	required	Task type: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'
quality_threshold	integer	optional	Minimum quality score required (0-100, default 85)

Raw schema

{
  "type": "object",
  "properties": {
    "task_type": {
      "description": "Task type: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'",
      "title": "Task Type",
      "type": "string"
    },
    "quality_threshold": {
      "default": 85,
      "description": "Minimum quality score required (0-100, default 85)",
      "title": "Quality Threshold",
      "type": "integer"
    }
  },
  "required": [
    "task_type"
  ],
  "title": "thinkneo_router_explainArguments"
}

thinkneo_compliance_generate

Generate a compliance report for regulatory frameworks (EU AI Act, ISO 42001, SOC2, NIST). Exports from live audit data.

Parameters3

workspace	string	optional	Workspace identifier
format	string	optional	Output format: ndjson or csv
framework	string	optional	Framework: eu-ai-act, iso-42001, soc2, nist

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "format": {
      "default": "ndjson",
      "description": "Output format: ndjson or csv",
      "title": "Format",
      "type": "string"
    },
    "framework": {
      "default": "eu-ai-act",
      "description": "Framework: eu-ai-act, iso-42001, soc2, nist",
      "title": "Framework",
      "type": "string"
    }
  },
  "title": "thinkneo_compliance_generateArguments"
}

thinkneo_sla_define

Define or update an SLA (Service Level Agreement) for an AI agent. Set accuracy, quality, cost, safety, or latency thresholds with automatic breach detection and configurable actions (alert, escalate, disable, switch_model). Like SRE SLOs but for AI agent outcomes. Requires authentication.

Parameters6

agent_name	string	required	Agent name to set SLA for (e.g., 'support-bot', 'finance-agent')
metric	string	required	Metric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg response ms)
threshold	number	required	Target threshold value (e.g., 95.0 for 95% accuracy)
window	string	optional	Rolling window: '1h', '24h', '7d', or '30d'
breach_action	string	optional	Action on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)
threshold_direction	string	optional	'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency).

Raw schema

{
  "type": "object",
  "properties": {
    "agent_name": {
      "description": "Agent name to set SLA for (e.g., 'support-bot', 'finance-agent')",
      "title": "Agent Name",
      "type": "string"
    },
    "metric": {
      "description": "Metric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg response ms)",
      "title": "Metric",
      "type": "string"
    },
    "threshold": {
      "description": "Target threshold value (e.g., 95.0 for 95% accuracy)",
      "title": "Threshold",
      "type": "number"
    },
    "window": {
      "default": "7d",
      "description": "Rolling window: '1h', '24h', '7d', or '30d'",
      "title": "Window",
      "type": "string"
    },
    "breach_action": {
      "default": "alert",
      "description": "Action on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)",
      "title": "Breach Action",
      "type": "string"
    },
    "threshold_direction": {
      "default": "min",
      "description": "'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency).",
      "title": "Threshold Direction",
      "type": "string"
    }
  },
  "required": [
    "agent_name",
    "metric",
    "threshold"
  ],
  "title": "thinkneo_sla_defineArguments"
}

thinkneo_sla_status

Check current SLA status for all agents or a specific agent. Shows actual metric values vs thresholds, healthy/breached status, and error budget remaining. Automatically records breaches. Requires authentication.

Parameters1

agent_name

any

optional

Optional: specific agent name. Leave empty for all agents.

Raw schema

{
  "type": "object",
  "properties": {
    "agent_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional: specific agent name. Leave empty for all agents.",
      "title": "Agent Name"
    }
  },
  "title": "thinkneo_sla_statusArguments"
}

thinkneo_sla_breaches

View SLA breach history — which SLAs were breached, by which agents, actual vs threshold values, and resolution status. Requires authentication.

Parameters2

days	integer	optional	Days to look back (default 30)
agent_name	any	optional	Filter by agent name

Raw schema

{
  "type": "object",
  "properties": {
    "days": {
      "default": 30,
      "description": "Days to look back (default 30)",
      "title": "Days",
      "type": "integer"
    },
    "agent_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by agent name",
      "title": "Agent Name"
    }
  },
  "title": "thinkneo_sla_breachesArguments"
}

thinkneo_sla_dashboard

SLA overview dashboard — all agents, current status, error budgets, and recent breaches (7d). The SRE dashboard for AI agents. Requires authentication.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "title": "thinkneo_sla_dashboardArguments"
}

thinkneo_audit_export

Export audit events from the live gateway. Supports JSON and CSV formats with date range filtering for SIEM integration.

Parameters4

workspace	string	optional	Workspace identifier
format	string	optional	Output format: ndjson or csv
start_date	any	optional	Start date ISO format
end_date	any	optional	End date ISO format

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "default",
      "description": "Workspace identifier",
      "title": "Workspace",
      "type": "string"
    },
    "format": {
      "default": "ndjson",
      "description": "Output format: ndjson or csv",
      "title": "Format",
      "type": "string"
    },
    "start_date": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Start date ISO format",
      "title": "Start Date"
    },
    "end_date": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "End date ISO format",
      "title": "End Date"
    }
  },
  "title": "thinkneo_audit_exportArguments"
}

thinkneo_compare_models

Compare available AI models from the live gateway catalog.

Parameters1

models

string

required

Comma-separated model IDs to compare (e.g. gpt-4o,claude-sonnet-4-20250514,gemini-2.5-flash)

Raw schema

{
  "type": "object",
  "properties": {
    "models": {
      "description": "Comma-separated model IDs to compare (e.g. gpt-4o,claude-sonnet-4-20250514,gemini-2.5-flash)",
      "title": "Models",
      "type": "string"
    }
  },
  "required": [
    "models"
  ],
  "title": "thinkneo_compare_modelsArguments"
}

thinkneo_count_tokens

Estimate token count for text (chars/4 approximation).

Parameters1

text

string

required

Text to estimate tokens for

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "description": "Text to estimate tokens for",
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "title": "thinkneo_count_tokensArguments"
}

thinkneo_optimize_prompt

Analyze prompt and suggest optimizations with live metrics context.

Parameters1

prompt

string

required

Prompt text to analyze

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "description": "Prompt text to analyze",
      "title": "Prompt",
      "type": "string"
    }
  },
  "required": [
    "prompt"
  ],
  "title": "thinkneo_optimize_promptArguments"
}

thinkneo_rotate_key

Instruct the gateway to rotate an API key.

Parameters1

key_prefix

string

required

First 8 chars of the key to rotate

Raw schema

{
  "type": "object",
  "properties": {
    "key_prefix": {
      "description": "First 8 chars of the key to rotate",
      "title": "Key Prefix",
      "type": "string"
    }
  },
  "required": [
    "key_prefix"
  ],
  "title": "thinkneo_rotate_keyArguments"
}

thinkneo_manage_secrets

Check connector grants and secrets status from the gateway.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "title": "thinkneo_manage_secretsArguments"
}

thinkneo_cache_status

Get semantic cache stats from the live gateway runtime metrics.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "title": "thinkneo_cache_statusArguments"
}

thinkneo_detect_injection

Detect prompt injection attempts in text using guardrail patterns. Also retrieves live guardrails_blocked stats from the gateway.

Parameters1

text

string

required

Text to analyze for injection attempts

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "description": "Text to analyze for injection attempts",
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "title": "thinkneo_detect_injectionArguments"
}

thinkneo_check_pii_international

Detect international PII across 30+ document types from 15+ countries: Brazil (CPF, CNPJ, RG, PIS), USA (SSN, EIN, ITIN, Passport), UK (NINO, UTR), Canada (SIN), EU (IBAN, VAT), Germany (Tax-ID), France (INSEE), Spain (DNI/NIE), Italy (Codice Fiscale), Argentina (CUIT), Mexico (CURP/RFC), Australia (TFN/ABN), India (Aadhaar/PAN), China (ID), Japan (My Number), and credit cards (Luhn validated). Required for LGPD/GDPR/HIPAA compliance. No authentication required.

Parameters2

text	string	required	Text to scan for PII (max 100,000 chars)
countries	array	optional	Filter by country codes (BR, US, UK, CA, EU, DE, FR, ES, IT, AR, MX, AU, IN, CN, JP, INTL). Empty = all.

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "description": "Text to scan for PII (max 100,000 chars)",
      "title": "Text",
      "type": "string"
    },
    "countries": {
      "default": [],
      "description": "Filter by country codes (BR, US, UK, CA, EU, DE, FR, ES, IT, AR, MX, AU, IN, CN, JP, INTL). Empty = all.",
      "items": {
        "type": "string"
      },
      "title": "Countries",
      "type": "array"
    }
  },
  "required": [
    "text"
  ],
  "title": "thinkneo_check_pii_internationalArguments"
}

thinkneo_alert_rule_list

List your configurable Monitor Agent alert rules. Each rule watches a metric (e.g. an API key reaching a % of its budget, workspace spend, error rate) and notifies your channels (email/discord/whatsapp) when it fires. Requires an admin API key.

Parameters1

workspace

string

optional

Workspace id (optional — defaults to the API key's workspace)

Raw schema

{
  "type": "object",
  "properties": {
    "workspace": {
      "default": "",
      "description": "Workspace id (optional — defaults to the API key's workspace)",
      "title": "Workspace",
      "type": "string"
    }
  },
  "title": "thinkneo_alert_rule_listArguments"
}

thinkneo_alert_rule_create

Create a Monitor Agent alert rule. Example: notify by email when API key 'X' reaches 75% of its budget → metric=key_spend_pct_of_budget, operator=gte, threshold=75, scope_value=<api_key_id>, budget_usd=<key budget>. Requires an admin API key.

Parameters10

name	string	required	Human-readable rule name
metric	string	required	One of: key_spend_24h_usd, key_spend_30d_usd, key_spend_pct_of_budget, workspace_error_rate_pct, workspace_max_rps, workspace_requests, workspace_spend_24h_usd, workspace_spend_30d_usd
threshold	number	required	Threshold value to compare the metric against
operator	string	optional	Comparison: gte, gt, lte, lt, eq
scope_value	string	optional	API key id — required for key_* metrics
budget_usd	number	optional	Key budget in USD — required for key_spend_pct_of_budget
severity	string	optional	low, medium, high, critical
channels	string	optional	Comma-separated: email, discord_webhook, whatsapp
cooldown_minutes	integer	optional	Minimum minutes between firings
workspace	string	optional	Workspace id (optional — defaults to the API key's workspace)

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Human-readable rule name",
      "title": "Name",
      "type": "string"
    },
    "metric": {
      "description": "One of: key_spend_24h_usd, key_spend_30d_usd, key_spend_pct_of_budget, workspace_error_rate_pct, workspace_max_rps, workspace_requests, workspace_spend_24h_usd, workspace_spend_30d_usd",
      "title": "Metric",
      "type": "string"
    },
    "threshold": {
      "description": "Threshold value to compare the metric against",
      "title": "Threshold",
      "type": "number"
    },
    "operator": {
      "default": "gte",
      "description": "Comparison: gte, gt, lte, lt, eq",
      "title": "Operator",
      "type": "string"
    },
    "scope_value": {
      "default": "",
      "description": "API key id — required for key_* metrics",
      "title": "Scope Value",
      "type": "string"
    },
    "budget_usd": {
      "default": 0,
      "description": "Key budget in USD — required for key_spend_pct_of_budget",
      "title": "Budget Usd",
      "type": "number"
    },
    "severity": {
      "default": "medium",
      "description": "low, medium, high, critical",
      "title": "Severity",
      "type": "string"
    },
    "channels": {
      "default": "email",
      "description": "Comma-separated: email, discord_webhook, whatsapp",
      "title": "Channels",
      "type": "string"
    },
    "cooldown_minutes": {
      "default": 60,
      "description": "Minimum minutes between firings",
      "title": "Cooldown Minutes",
      "type": "integer"
    },
    "workspace": {
      "default": "",
      "description": "Workspace id (optional — defaults to the API key's workspace)",
      "title": "Workspace",
      "type": "string"
    }
  },
  "required": [
    "name",
    "metric",
    "threshold"
  ],
  "title": "thinkneo_alert_rule_createArguments"
}

thinkneo_alert_rule_delete

Delete a Monitor Agent alert rule by its rule_id. Requires an admin API key.

Parameters2

rule_id	string	required	The rule_id to delete (from thinkneo_alert_rule_list)
workspace	string	optional	Workspace id (optional — defaults to the API key's workspace)

Raw schema

{
  "type": "object",
  "properties": {
    "rule_id": {
      "description": "The rule_id to delete (from thinkneo_alert_rule_list)",
      "title": "Rule Id",
      "type": "string"
    },
    "workspace": {
      "default": "",
      "description": "Workspace id (optional — defaults to the API key's workspace)",
      "title": "Workspace",
      "type": "string"
    }
  },
  "required": [
    "rule_id"
  ],
  "title": "thinkneo_alert_rule_deleteArguments"
}

thinkneo_alert_rule_test

Send a test notification through a rule's configured channels to confirm delivery (email/discord/whatsapp). Requires an admin API key.

Parameters2

rule_id	string	required	The rule_id to test (from thinkneo_alert_rule_list)
workspace	string	optional	Workspace id (optional — defaults to the API key's workspace)

Raw schema

{
  "type": "object",
  "properties": {
    "rule_id": {
      "description": "The rule_id to test (from thinkneo_alert_rule_list)",
      "title": "Rule Id",
      "type": "string"
    },
    "workspace": {
      "default": "",
      "description": "Workspace id (optional — defaults to the API key's workspace)",
      "title": "Workspace",
      "type": "string"
    }
  },
  "required": [
    "rule_id"
  ],
  "title": "thinkneo_alert_rule_testArguments"
}

training_dataset_attest

Attest a training dataset (hash-chained governance audit). Returns a receipt with ledger_id + chain_hash + signature. Idempotent by (tenant, workspace, project, idempotency_key).

Parameters7

dataset_hash	string	required	SHA-256 of the full dataset manifest content
manifest_hash	string	required	SHA-256 of the manifest.json
source	object	required	Provenance: e.g. {'kind':'huggingface','repo':'...','revision':'...'}
episode_hashes_len	integer	required	Number of episodes covered by this attestation
tags	any	optional	Optional free-form tags
actor	any	optional	Optional actor email override (defaults to key owner)
idempotency_key	any	optional	Client-supplied idempotency key. Replaying returns same receipt.

Raw schema

{
  "type": "object",
  "properties": {
    "dataset_hash": {
      "description": "SHA-256 of the full dataset manifest content",
      "title": "Dataset Hash",
      "type": "string"
    },
    "manifest_hash": {
      "description": "SHA-256 of the manifest.json",
      "title": "Manifest Hash",
      "type": "string"
    },
    "source": {
      "additionalProperties": true,
      "description": "Provenance: e.g. {'kind':'huggingface','repo':'...','revision':'...'}",
      "title": "Source",
      "type": "object"
    },
    "episode_hashes_len": {
      "description": "Number of episodes covered by this attestation",
      "minimum": 0,
      "title": "Episode Hashes Len",
      "type": "integer"
    },
    "tags": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional free-form tags",
      "title": "Tags"
    },
    "actor": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional actor email override (defaults to key owner)",
      "title": "Actor"
    },
    "idempotency_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Client-supplied idempotency key. Replaying returns same receipt.",
      "title": "Idempotency Key"
    }
  },
  "required": [
    "dataset_hash",
    "manifest_hash",
    "source",
    "episode_hashes_len"
  ],
  "title": "training_dataset_attestArguments"
}

training_run_start

Attest the start of a training run. Binds dataset hashes + config hash + code hash into a governed run_id. Idempotent by (tenant, workspace, project, idempotency_key).

Parameters10

dataset_hashes	array	required	Dataset hashes consumed by this run
config	object	required	Full training config as JSON
config_hash	string	required	SHA-256 of the canonicalized config
code_hash	string	required	SHA-256 of the training-code tree (or commit sha)
seed	integer	optional	RNG seed
framework	string	optional	Training framework (lerobot, tf, torch...)
policy_arch	string	optional	Policy architecture (act, diffusion, pi0.5...)
parent_run_id	any	optional	Optional parent run for continued/forked training
actor	any	optional	Optional actor email override
idempotency_key	any	optional	Idempotency key

Raw schema

{
  "type": "object",
  "properties": {
    "dataset_hashes": {
      "description": "Dataset hashes consumed by this run",
      "items": {
        "type": "string"
      },
      "title": "Dataset Hashes",
      "type": "array"
    },
    "config": {
      "additionalProperties": true,
      "description": "Full training config as JSON",
      "title": "Config",
      "type": "object"
    },
    "config_hash": {
      "description": "SHA-256 of the canonicalized config",
      "title": "Config Hash",
      "type": "string"
    },
    "code_hash": {
      "description": "SHA-256 of the training-code tree (or commit sha)",
      "title": "Code Hash",
      "type": "string"
    },
    "seed": {
      "default": 0,
      "description": "RNG seed",
      "minimum": 0,
      "title": "Seed",
      "type": "integer"
    },
    "framework": {
      "default": "lerobot",
      "description": "Training framework (lerobot, tf, torch...)",
      "title": "Framework",
      "type": "string"
    },
    "policy_arch": {
      "default": "act",
      "description": "Policy architecture (act, diffusion, pi0.5...)",
      "title": "Policy Arch",
      "type": "string"
    },
    "parent_run_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional parent run for continued/forked training",
      "title": "Parent Run Id"
    },
    "actor": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional actor email override",
      "title": "Actor"
    },
    "idempotency_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Idempotency key",
      "title": "Idempotency Key"
    }
  },
  "required": [
    "dataset_hashes",
    "config",
    "config_hash",
    "code_hash"
  ],
  "title": "training_run_startArguments"
}

training_run_trace

Stream one training-step metrics batch for a governed run. High-volume path — NOT ledger-anchored. Idempotent by (run_id, step).

Parameters3

run_id	string	required	Run id returned by training_run_start
step	integer	required	Training step index (monotonic)
metrics	object	required	Metrics dict, e.g. {'loss':..., 'lr':..., 'grad_norm':...}

Raw schema

{
  "type": "object",
  "properties": {
    "run_id": {
      "description": "Run id returned by training_run_start",
      "title": "Run Id",
      "type": "string"
    },
    "step": {
      "description": "Training step index (monotonic)",
      "minimum": 0,
      "title": "Step",
      "type": "integer"
    },
    "metrics": {
      "additionalProperties": true,
      "description": "Metrics dict, e.g. {'loss':..., 'lr':..., 'grad_norm':...}",
      "title": "Metrics",
      "type": "object"
    }
  },
  "required": [
    "run_id",
    "step",
    "metrics"
  ],
  "title": "training_run_traceArguments"
}

training_policy_trust_score

Compute and attest a Policy Trust Score (0-100) for a training checkpoint. Score + breakdown + evaluator version are anchored to the ledger.

Parameters6

run_id	string	required	Run id
checkpoint_hash	string	required	SHA-256 of the checkpoint bytes
score	integer	required	Trust score 0-100
breakdown	object	required	Per-dimension breakdown (safety, oo_d, snapshot_age, etc.)
snapshot_age_s	integer	required	Age of the checkpoint snapshot in seconds
evaluator_version	string	required	Evaluator version tag, e.g. 'trust-score-v1'

Raw schema

{
  "type": "object",
  "properties": {
    "run_id": {
      "description": "Run id",
      "title": "Run Id",
      "type": "string"
    },
    "checkpoint_hash": {
      "description": "SHA-256 of the checkpoint bytes",
      "title": "Checkpoint Hash",
      "type": "string"
    },
    "score": {
      "description": "Trust score 0-100",
      "maximum": 100,
      "minimum": 0,
      "title": "Score",
      "type": "integer"
    },
    "breakdown": {
      "additionalProperties": true,
      "description": "Per-dimension breakdown (safety, oo_d, snapshot_age, etc.)",
      "title": "Breakdown",
      "type": "object"
    },
    "snapshot_age_s": {
      "description": "Age of the checkpoint snapshot in seconds",
      "minimum": 0,
      "title": "Snapshot Age S",
      "type": "integer"
    },
    "evaluator_version": {
      "description": "Evaluator version tag, e.g. 'trust-score-v1'",
      "title": "Evaluator Version",
      "type": "string"
    }
  },
  "required": [
    "run_id",
    "checkpoint_hash",
    "score",
    "breakdown",
    "snapshot_age_s",
    "evaluator_version"
  ],
  "title": "training_policy_trust_scoreArguments"
}

training_deploy_attest

Attest deployment of a checkpoint to a target (sim, shadow, prod). Records gate_verdict + trust_score at deploy time. Idempotent by (tenant, workspace, project, idempotency_key).

Parameters8

run_id	string	required	Run id
checkpoint_hash	string	required	Checkpoint hash being deployed
gate_verdict	object	required	Gate verdict dict (rules, pass/fail, reasons)
trust_score	integer	required	Trust score at deploy time
target_id	string	required	Target identifier (device / cluster / robot fleet id)
environment	string	required	Environment: sim \| shadow \| prod
actor	any	optional	Optional actor email override
idempotency_key	any	optional	Idempotency key

Raw schema

{
  "type": "object",
  "properties": {
    "run_id": {
      "description": "Run id",
      "title": "Run Id",
      "type": "string"
    },
    "checkpoint_hash": {
      "description": "Checkpoint hash being deployed",
      "title": "Checkpoint Hash",
      "type": "string"
    },
    "gate_verdict": {
      "additionalProperties": true,
      "description": "Gate verdict dict (rules, pass/fail, reasons)",
      "title": "Gate Verdict",
      "type": "object"
    },
    "trust_score": {
      "description": "Trust score at deploy time",
      "maximum": 100,
      "minimum": 0,
      "title": "Trust Score",
      "type": "integer"
    },
    "target_id": {
      "description": "Target identifier (device / cluster / robot fleet id)",
      "title": "Target Id",
      "type": "string"
    },
    "environment": {
      "description": "Environment: sim | shadow | prod",
      "title": "Environment",
      "type": "string"
    },
    "actor": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional actor email override",
      "title": "Actor"
    },
    "idempotency_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Idempotency key",
      "title": "Idempotency Key"
    }
  },
  "required": [
    "run_id",
    "checkpoint_hash",
    "gate_verdict",
    "trust_score",
    "target_id",
    "environment"
  ],
  "title": "training_deploy_attestArguments"
}

training_audit_event

Append a training-domain audit event to the compliance ledger. kind ∈ {rollback, manual_review, alert, governance_verdict, sim2real_iteration}.

Parameters4

kind	string	required	One of: rollback, manual_review, alert, governance_verdict, sim2real_iteration
ref	object	required	Reference dict, e.g. {'run_id':..., 'checkpoint_hash':...}
payload	object	required	Event payload (schema depends on kind)
actor	any	optional	Optional actor email override

Raw schema

{
  "type": "object",
  "properties": {
    "kind": {
      "description": "One of: rollback, manual_review, alert, governance_verdict, sim2real_iteration",
      "title": "Kind",
      "type": "string"
    },
    "ref": {
      "additionalProperties": true,
      "description": "Reference dict, e.g. {'run_id':..., 'checkpoint_hash':...}",
      "title": "Ref",
      "type": "object"
    },
    "payload": {
      "additionalProperties": true,
      "description": "Event payload (schema depends on kind)",
      "title": "Payload",
      "type": "object"
    },
    "actor": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional actor email override",
      "title": "Actor"
    }
  },
  "required": [
    "kind",
    "ref",
    "payload"
  ],
  "title": "training_audit_eventArguments"
}

README.md8 KBView on GitHub

ThinkNEO MCP Server

Open MCP server with built-in defense layer (ThinkShield). Part of the ThinkNEO Platform — enterprise AI governance.

What This Is

An open-source MCP server providing 72 tools for AI governance, observability, and security:

ThinkShield — Production defense layer: detection engine, 5 rule packs, runtime middleware. 145 tests, p99 < 1ms.
72 MCP Tools — Governance, guardrails, FinOps, smart routing, observability, compliance, outcome validation, and more.
24 A2A Skills — Bidirectional MCP-A2A bridge for Google's Agent-to-Agent Protocol (v0.3.0, Linux Foundation).
Apache-2.0 — Use it, fork it, contribute.

What This Is Not

Not the full ThinkNEO Platform. Governance orchestration, cryptographic audit chain, tenant management, and enterprise integrations are proprietary and run at thinkneo.ai.
Not a standalone security product. ThinkShield is the defense component of a larger governed platform.

Why Open

We open-source our defense layer because real security doesn't depend on hidden rules — it depends on tested, audited, continuously improved detection plus a strong governance moat around it.

Snort. Suricata. Falco. OWASP CRS. The security industry runs on open detection. We follow that tradition.

The detection is open. The governance is proprietary. That's where the moat is.

Architecture

code

                        Open Source (this repo)                    Proprietary (thinkneo.ai)
                   ┌─────────────────────────────────┐     ┌──────────────────────────────────┐
                   │                                 │     │                                  │
  MCP Clients ────>│  72 MCP Tools                   │     │  Governance Orchestration         │
  (Claude, Cursor, │  ├── Guardrails & Safety        │────>│  ├── Policy Engine (AIRGP)        │
   ChatGPT, etc.)  │  ├── FinOps & Smart Routing     │     │  ├── Cryptographic Audit Chain    │
                   │  ├── Observability              │     │  ├── Tenant Management            │
  A2A Agents ─────>│  ├── Compliance & Validation    │     │  ├── Enterprise Integrations      │
  (Google A2A)     │  └── MCP-A2A Bridge (24 skills) │     │  └── SLA & Support                │
                   │                                 │     │                                  │
                   │  ThinkShield Defense Layer       │     │  SHA-256 Hash Chain (949K+ rows)  │
                   │  ├── Detection Engine            │     │  Stripe Billing                   │
                   │  ├── 5 Rule Packs               │     │  Resend Email                     │
                   │  └── ASGI Middleware             │     │  Multi-tenant Auth                │
                   │                                 │     │                                  │
                   └─────────────────────────────────┘     └──────────────────────────────────┘
                          Apache-2.0 License                      Commercial License

Quickstart

bash

# Clone
git clone https://github.com/thinkneo-ai/mcp-server.git
cd mcp-server

# Install
pip install -r requirements.txt

# Run
python -m uvicorn src.server:app --host 0.0.0.0 --port 8081

# Test
python -m pytest tests/ -q

Or with Docker:

bash

cd deploy
docker compose up -d

Connect from Claude Desktop, Cursor, or any MCP client:

code

https://mcp.thinkneo.ai/mcp

Free tier: 500 calls/month, auto-provisioned API key. All 72 tools available.

Components

Directory	Description	License
`src/tools/`	72 MCP tools — governance, security, FinOps, observability	Apache-2.0
`src/thinkshield/`	Defense layer — detection engine, 5 rule packs	Apache-2.0
`tests/thinkshield/`	ThinkShield test suite — 145 tests + attack/benign fixtures	Apache-2.0
`agent.json`	A2A Agent Card — 24 skills bridged from MCP	Apache-2.0

ThinkShield Rule Packs

Pack	Detects
`injection`	SQL injection, XSS, command injection, path traversal
`auth`	Credential stuffing, brute force, token replay, privilege escalation
`abuse`	Rate abuse, resource exhaustion, API scraping
`recon`	Path probing, tool enumeration, method probing, fingerprinting
`headers`	Header anomalies, spoofing, missing security headers

MCP Tools (72)

Full tool reference: docs/quickstart.md

MCP Spec Compliance

Complete Model Context Protocol 2024-11-05 implementation. Forward-compatible with MCP 2025-03-26.

Capability	Status	Details
tools	72 tools, full annotations	destructiveHint, readOnlyHint, idempotentHint, openWorldHint
resources	2 resources	Getting Started guide, Supported Providers
prompts	2 prompts with completions	governance_audit, policy_preflight
logging	logging/setLevel	8 levels, per-session, audit trail
completions	completion/complete	workspace (auth-scoped), provider, model (provider-aware)

Ecosystem

This repo is part of the ThinkNEO ecosystem:

Project	Description
ThinkNEO Platform	Enterprise AI governance platform
AIRGP	AI Runtime Governance Protocol — open standard
A2ASTC	A2A Security & Trust Conformance
ThinkNEO SMB Hub	Business applications for SMBs
Robotics Governance	Robot fleet governance dashboard

Security

See SECURITY.md for vulnerability reporting.

Contributing

See CONTRIBUTING.md.

Server	Description	Tools
thinkneo-control-plane	Enterprise AI Control Plane (this repo)	72 tools
thinkneo-mcp-smb-products	SMB standalone products — self-serve via TNC credits	37 tools

License

Apache-2.0 — see LICENSE.

About

ThinkNEO AI Technology Co., Ltd. — Hong Kong CR No. 2296774.

Built by the team behind the ThinkNEO Enterprise AI Control Plane, AIRGP protocol, and A2ASTC conformance suite.

NVIDIA Inception | Anthropic Partner | Linux Foundation A2A

Install

Tools (74)

thinkneo_check_spendthinkneo_completethinkneo_read_memorythinkneo_write_memorythinkneo_evaluate_guardrailthinkneo_checkthinkneo_check_policythinkneo_get_budget_status

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.thinkneo.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "control-plane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.thinkneo.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.