Plith

Official15 tools

by plith

AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.

Infrastructure for AI agents with cost prediction, validation, governance, and failure intelligence.

Captured live from the server via tools/list.

dedupq_check

Before executing any LLM task, check if an identical or semantically similar task has already been completed. Returns cached result on hit, saving one LLM call. On a miss, execute your task and call dedupq_complete to cache the result for future hits. Costs 1 credit.

Parameters (4)

contentstringrequired
The task content to check for duplicates. This is hashed and embedded for matching.
task_idstring
Optional caller task ID for tracing and cross-referencing with BurnRate.
hash_onlyboolean
If true, skip vector similarity search and use exact hash matching only. Default: false.
similarity_thresholdnumber
Cosine similarity threshold for semantic matching, 0.0 to 1.0. Default: 0.80.

dedupq_complete

After executing a task, store the result so future identical or similar tasks return a cache hit via dedupq_check. Costs 2 credits.

Parameters (4)

contentstringrequired
Original task content. Used to compute hash and embedding for future matching.
resultanyrequired
The task result to cache. Can be any JSON value.
task_idstring
Optional task ID. Used as the database row ID if provided.
hash_onlyboolean
If true, skip embedding generation. Default: false.

burnrate_estimate

Before executing a multi-step agent plan, estimate the total LLM cost. Returns per-step breakdown and optimization suggestions. If the estimate exceeds your budget, pipe the same plan into burnrate_optimize. Costs 1 credit.

Parameters (1)

planarrayrequired
Array of plan steps with provider, model, and token estimates.

burnrate_track

Log the actual cost of an LLM call after execution. Call this after every LLM request to build calibration data that improves burnrate_estimate accuracy over time. Free — no credits charged. Returns the recorded cost entry with computed margin versus the prior estimate when one exists for this model and token range.

Parameters (6)

providerstringrequired
LLM provider identifier. Supported: anthropic, openai, google, mistral, cohere, deepseek, together, fireworks, groq. Must match the provider of the model used.
modelstringrequired
Model identifier as returned by the provider. Examples: claude-sonnet-4-6, gpt-4o, gemini-2.0-flash, mistral-large-latest. Unknown models are accepted but cost may show as $0.
input_tokensnumberrequired
Actual prompt tokens used. Must be >= 0.
output_tokensnumberrequired
Actual completion tokens used. Must be >= 0.
task_idstring
Optional task ID for cross-referencing spend with DedupQ deduplication results. Use the same task_id passed to dedupq_check to link cost tracking with deduplication.
cache_read_tokensnumber
Optional. Cache-read tokens.

burnrate_optimize

Get a cheaper equivalent plan by substituting models with lower-cost alternatives. Call after burnrate_estimate if the estimated cost exceeds your budget. Returns the optimized plan with substituted models, new per-step costs, total savings, and whether the target_budget is met. Optionally set target_budget to constrain the optimization. Costs 1 credit.

Parameters (2)

planarrayrequired
Array of plan steps. Same schema as burnrate_estimate: each step needs step, provider, model, estimated_input_tokens, estimated_output_tokens.
target_budgetnumber
Optional. Target total cost in USD.

burnrate_budget

Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged.

Parameters (1)

daily_limitnumber
Optional. Daily budget in USD (e.g., 10.0 for a $10/day cap). Enables budget alerts and remaining-balance calculation.

qualitygate_validate

After your agent generates output, validate it against your rules before shipping. Runs deterministic checks (regex, JSON schema, syntax) plus optional LLM-powered tone and factual analysis. Returns a structured verdict (pass, warn, or fail) with a 0-100 score and per-check issue details. Use qualitygate_trends to spot recurring failure patterns over time. Variable cost: 1 credit per deterministic check, 8 credits per LLM check.

Parameters (7)

outputstringrequired
The agent output text to validate.
directivesarray
Directive objects. Types: must_include, must_not_include, must_match, must_not_match, must_contain, must_not_contain, min_length, max_length.
schemaobject
JSON Schema to validate output against.
languagestring
Code language for syntax check: json, python, javascript, typescript.
check_typesarray
Checks to run. Auto-inferred if omitted.
overrideboolean
Force pass. Requires override_reason.
override_reasonstring
Required when override is true.

guardrail_check

Evaluate a proposed agent action against your governance policies. Returns allow or deny with the matched policy reason. Requires at least one active policy created via guardrail_create_policy. Deterministic rule evaluation — no LLM. Costs 1 credit.

Parameters (2)

agent_idstringrequired
Agent identifier.
proposed_actionobjectrequired
Action to evaluate. Must contain a 'type' field. Example: {"type": "http_request", "url": "https://external.example.com"} or {"type": "file_write", "path": "/etc/config"}.

guardrail_create_policy

Create a persistent governance policy that guardrail_check evaluates on every subsequent call. Define rules using and/or/not operators over action types, resource patterns, and budget thresholds. Call this before using guardrail_check — checks require at least one active policy. Policies persist until explicitly deleted. Duplicate policy names return an error. Returns the created policy with its ID and active status.

Parameters (5)

namestringrequired
Unique policy name per org. Examples: 'no-delete-in-prod', 'budget-cap-50', 'pii-block'.
descriptionstring
Optional human-readable summary of what this policy enforces. Returned in guardrail_check responses and guardrail_list_policies output for auditability.
rulesarrayrequired
Array of rule objects evaluated against the proposed_action in guardrail_check. Leaf operators: eq, starts_with, contains, gt, lt (compare field to value). Compound operators: and, or, not (nest sub-rules in a rules array). Example: [{operator:'eq', field:'type', value:'file_write'}] blocks all file writes. Nested example: [{operator:'and', rules:[{operator:'eq',field:'type',value:'api_call'},{operator:'contains',field:'url',value:'prod'}]}] blocks prod API calls.
action_typesarray
Optional. Restrict this policy to only evaluate when proposed_action.type matches one of these values. Examples: ['file_write', 'api_call', 'db_delete']. Omit to apply the policy to all action types regardless of type field.
prioritynumber
Optional. Evaluation order. Default: 0.

pitfalldb_query

Check for known failure patterns before executing a task type. Returns pitfalls with severity, fix suggestions, and confidence scores. After your agent runs, submit failures via pitfalldb_report so others benefit. Costs 2 credits.

Parameters (3)

task_typestringrequired
Task category: code_generation, web_search, data_analysis, etc.
task_descriptionstring
Optional. Natural-language task description for semantic search.
filtersobject
Optional filters.

pitfalldb_report

Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged.

Parameters (3)

task_typestringrequired
Task category.
task_descriptionstringrequired
Description of the failed task.
failureobjectrequired
Failure details.

rigor_plan

Before executing a complex task, get a structured workflow plan with per-step cost estimates. Classifies your task, selects the optimal framework sequence, and returns the full plan without executing anything. Free — no credits charged.

Parameters (3)

task_descriptionstringrequired
Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'
task_typestring
Optional hint to bypass automatic classification. Values: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation.
preferencesobject
Optional workflow preferences.

rigor_execute

Execute a structured workflow end-to-end. Call rigor_plan first (free) to preview the step sequence and cost estimate before committing credits. Classifies the task, selects the optimal tool sequence, and executes each step with the right LLM model. Returns a complete deliverable — solution designs, competitive analyses, governance documents, and more. Supports SSE streaming for real-time progress, webhook callback, or polling.

Parameters (5)

task_descriptionstringrequired
Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'
task_typestring
Optional hint to bypass automatic classification. Values: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation.
deliveryobject
Delivery method. Default: polling (MCP clients typically can't handle SSE).
preferencesobject
Optional workflow preferences.
contextobject
Additional context for the workflow.

rigor_status

Check the status of a running or completed Rigor workflow. Returns progress, step results, and the full deliverable when complete. Use after rigor_execute with polling delivery to retrieve results.

Parameters (1)

workflow_idstringrequired
The workflow ID returned by rigor_execute (format: wr_xxx).

rigor_workflows

List all Rigor workflows for your organization with filtering and pagination. Returns status, progress, capacity usage, and available actions per workflow. Use to monitor workflow state, understand concurrent limit usage, and identify stuck or completed workflows.

Parameters (5)

statusstring
Filter by status (comma-separated). Valid values: executing, step_executing, completed, failed, halted, pending_approval, cancelled. E.g. "halted,failed,pending_approval"
task_typestring
Filter by classified task type
counts_toward_limitstring
Filter to workflows counting toward the concurrent limit
limitnumber
Page size (default 20, max 100)
cursorstring
Pagination cursor (created_at timestamp from previous page)

Install

Remote endpoint

Streamable HTTP

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

url

https://plith.ai/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "plith": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://plith.ai/api/mcp"
      ]
    }
  }
}

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