Skip to content
MCP server

SynomosAI Governance MCP

Self-assess AI agent governance: A3 scorecard, ISO 42001 evidence and PII scan

Runs locallyStatus and history
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
1.2.2
Listing updated
2 days ago

About SynomosAI Governance MCP

SynomosAI Governance MCP is an open-source MCP server for security. It runs locally on your machine and is started by your AI client.

Six local tools cover governance paperwork. a3_assess scores four dimensions (intent, impact, reversibility, oversight, 1 to 5 each, total 20) and returns release, conditional or reject with a reason. audit_evidence_chain supplies six ISO/IEC 42001 and NIST AI RMF templates: decision log, risk register, model card, change record, human-oversight proof and incident ledger. compliance_checklist references EU AI Act clauses, GB/Z 185, ISO 42001 and PIPL or GDPR.

The gov_scan tool screens text for phone numbers, emails, local paths, credential-like strings and key fingerprints. passport_lookup queries a local identity ledger and lgd_knowledge returns material from the author's Lifecycle Governance Doctrine. The server uses only the Python standard library, makes no network calls, and attaches a trace_id to each response, with an optional JSONL audit log.

The README is explicit that outputs are self-assessment artifacts, not third-party certification, and regulatory references are for orientation only. It follows an install-by-consent model, and a hosted version is offered on ModelScope. MIT code, CC BY 4.0 docs.

Install

Run in a terminal

claude mcp add synomosai-governance-mcp -- uvx synomosai-governance-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "synomosai-governance-mcp": {
      "command": "uvx",
      "args": [
        "synomosai-governance-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "synomosai-governance-mcp": {
      "command": "uvx",
      "args": [
        "synomosai-governance-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "synomosai-governance-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "synomosai-governance-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "synomosai-governance-mcp": {
      "command": "uvx",
      "args": [
        "synomosai-governance-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "synomosai-governance-mcp": {
      "command": "uvx",
      "args": [
        "synomosai-governance-mcp"
      ]
    }
  }
}

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

a3_assess
Four-dimension scorecard giving release, conditional or reject
audit_evidence_chain
Six ISO 42001 and NIST AI RMF evidence templates
compliance_checklist
Registration-readiness checklist against EU AI Act and other standards
passport_lookup
Passport or identity-code lookup against a local ledger
gov_scan
Screen text for contact details, paths and credential-like strings
lgd_knowledge
Lifecycle Governance Doctrine knowledge endpoint

What it does

A3 scorecard
Four-dimension score leading to release, conditional or reject.
Evidence templates
Six ISO 42001 and NIST AI RMF artifacts.
Compliance checklist
References EU AI Act, GB/Z 185, ISO 42001, PIPL and GDPR.
Text screening
Finds contact details, local paths and credential-like strings.
Zero dependencies
Pure Python standard library with no network egress.
Traceable calls
Each response has a trace_id and optional audit log.

Good for

  • Score an AI agent release before shipping
  • Generate evidence templates for an ISO 42001 audit
  • Scan text for secrets before publishing
  • Prepare a registration-readiness checklist

Pricing

Open source

Free; code is MIT licensed.

SynomosAI Governance MCP FAQ

Is it a certification?

No. Outputs are self-assessment artifacts, not third-party certification.

Does it send data over the network?

The README says zero network egress.

What does it need?

Python 3.9 or newer and no third-party packages.

What licence applies?

Code is MIT; docs are CC BY 4.0.

Is SynomosAI Governance MCP free?

Yes. SynomosAI Governance MCP is open source, so you can use and self-host it for free.

How do I add SynomosAI Governance MCP to Claude Code?

Run this command in your terminal: claude mcp add synomosai-governance-mcp -- uvx synomosai-governance-mcp

What are the best alternatives to SynomosAI Governance MCP?

The closest alternatives to SynomosAI Governance MCP are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

Alternatives to SynomosAI Governance MCP

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  4. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security
  5. SecureCloud

    MCP server

    SentinelOne and IT security catalog, prices, quotes and checkout links for Israel

    • 7 tools
    • Remote
    • Free
    • Security