io.github.jdhart81/security-preflight

Official5 toolsLive

by jdhart81 · Python

Static MCP, source-code and injection-indicator checks with redacted signed receipts.

Evidence-bounded static agent security checks with signed redacted receipts. The server, io.github.jdhart81/security-preflight, is described alongside an agent-fleet setup that provides paid, deterministic HTTP routes for a carbon and compliance workflow and includes an MCP security preflight step. It exposes 3 tools.

🛠️ Key Features

Evidence-bounded static agent security checks
Signed redacted receipts
Includes an MCP security preflight step

🚀 Use Cases

Preflight security checks for agent execution
Supporting a five-step carbon and compliance workflow: measure → account → disclose → claim → scan

⚡ Developer Benefits

Deterministic, evidence-bounded security checks
Security results include signed redacted receipts

⚠️ Limitations

Described as part of a broader “paid HTTP routes” agent-fleet system; details of the preflight tool behavior beyond that excerpt are not provided

Topics

agent-securityai-agentsdeveloper-toolsmcpmcp-serverpolicy-as-codepythonsecurity-toolsx402

Captured live from the server via tools/list.

security_preflight

Run a $1 static Security Preflight and return a signed receipt. New x402 payer wallets may receive the fleet-wide $0.01 introductory call. No deployed endpoint is fetched or tested. Importing the receipt into an Agent Market profile is a separate, explicit action.

Parameters7

agent_id	string	required
manifest	object	required
subject_profile_sha256	any	optional
policy	any	optional
sample_inputs	any	optional
payment_ref	any	optional
request_id	any	optional

Raw schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "title": "Agent Id",
      "type": "string"
    },
    "manifest": {
      "additionalProperties": true,
      "title": "Manifest",
      "type": "object"
    },
    "subject_profile_sha256": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Subject Profile Sha256"
    },
    "policy": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Policy"
    },
    "sample_inputs": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Sample Inputs"
    },
    "payment_ref": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Payment Ref"
    },
    "request_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Request Id"
    }
  },
  "required": [
    "agent_id",
    "manifest"
  ],
  "title": "security_preflightArguments"
}

scan_source

$1 bounded inline VulnCanon source scan; indicators, not proven exploits. At most 64 KiB, 2000 lines, 4096 characters per line. No model calls, repository fetching or code execution. Returns a redacted signed receipt.

Parameters2

agent_id	string	required
source	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "title": "Agent Id",
      "type": "string"
    },
    "source": {
      "title": "Source",
      "type": "string"
    }
  },
  "required": [
    "agent_id",
    "source"
  ],
  "title": "scan_sourceArguments"
}

screen_injection

$1 batch of 1–20 text samples screened for deterministic injection markers. Maximum 64 KiB total. Heuristic indicators, not calibrated probabilities or a guarantee of safety. No model calls or automatic follow-on purchase.

Parameters2

agent_id	string	required
texts	array	required

Raw schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "title": "Agent Id",
      "type": "string"
    },
    "texts": {
      "items": {
        "type": "string"
      },
      "title": "Texts",
      "type": "array"
    }
  },
  "required": [
    "agent_id",
    "texts"
  ],
  "title": "screen_injectionArguments"
}

get_security_receipt

Read a previously issued public, input-redacted receipt.

Parameters1

receipt_id

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "receipt_id": {
      "title": "Receipt Id",
      "type": "string"
    }
  },
  "required": [
    "receipt_id"
  ],
  "title": "get_security_receiptArguments"
}

describe_agent

Describe scope, evidence boundary, inputs, and outputs.

Parameters

No parameters.

Raw schema

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

README.md2 KBView on GitHub

Viridis Agent Fleet: open-source agents for the agent economy

Deterministic, auditable MCP agents: trust and settlement rails (identity, trust, escrow, metering, arbitration, notary, surety, provenance, covenant, offsets, compute-ledger) and priced-grade services (tax credits, GHG accounting, construction takeoff, measurement, compliance). Every core is pure Python with no LLM in the serving path, and every result is content-addressed so anyone can re-verify it.

Licensed Apache-2.0. Run any agent yourself, fork it, embed it.

Run an agent locally (free, forever)

bash

pip install -r requirements-dev.txt
python3 agent-escrow-agent/adapters/mcp_server.py          # stdio MCP
python3 run_fleet_tests.py                                 # every agent's invariant tests

Or use the hosted fleet

https://mcp.viridisconservation.com runs all agents as one managed MCP service:

	Self-hosted (this repo)	Hosted by Viridis
Agent logic & verification	✅ identical	✅ identical
Viridis-signed receipts & notary chain	–	✅
Shared trust/reputation network data	–	✅
Maintained rule packs (tax, GHG factors, regs)	snapshot	✅ kept current
Payments (x402, card), seats, SLA	–	✅

Free tier: 10 calls/day per service; the rails (identity, escrow, metering…) are free forever. Verification is always free.

Boundary

This repo contains agent cores, MCP adapters, tests, standards and self-host tooling. The hosted service layer (gateway, payment and settlement, seats, signing authority, operations, telemetry and customer data) is proprietary and is not in this repo. Please don't open PRs that add it.

"Viridis", "Viridis Conservation" and the Viridis marks are trademarks of Viridis LLC; see TRADEMARKS.md.

Install

Tools (5)

security_preflightscan_sourcescreen_injectionget_security_receiptdescribe_agent

Remote endpoint

Streamable HTTP

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

url

https://mcp.viridis-security.com/security-preflight/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "security-preflight": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.viridis-security.com/security-preflight/mcp"
      ]
    }
  }
}

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

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

security_preflight

scan_source

screen_injection

get_security_receipt

describe_agent

Viridis Agent Fleet: open-source agents for the agent economy

Run an agent locally (free, forever)

Or use the hosted fleet

Boundary

Install

Remote endpoint

Related servers