A MCP server for AI governance evidence collection and automation. It maps a single tool call to EU AI Act, ISO 42001, SOC 2, and NIST AI RMF, pushing compliance evidence to Mima from any agent or stack with minimal configuration.

🛠️ Key Features

Maps one tool call to multiple compliance standards (EU AI Act, ISO 42001, SOC 2, NIST AI RMF)
Pushes governance evidence to Mima from any agent or stack
Requires only 4 lines of configuration
Automatic readiness score updates

🚀 Use Cases

Automate evidence collection for AI governance programs
Demonstrate compliance alignment across standards
Integrate with diverse agent stacks to centralize MCP data
Provide real-time readiness reporting to stakeholders

⚡ Developer Benefits

Simple integration with minimal boilerplate
Consistent compliance mapping across frameworks
Accessible README and repository metadata for quick onboarding
Clear evidence push workflow to Mima

⚠️ Limitations

Based on readme excerpt; detailed capabilities depend on implementation in codebase
Requires environment capable of executing 4-line config setup
Behavior may vary with agent/tooling ecosystem not listed in topics

@mima-ai/governance-mcp

MCP server for AI governance — push compliance evidence to Mima from any agent, any stack, 4 lines of config.

One tool call maps to EU AI Act, ISO 42001, SOC 2, and NIST AI RMF simultaneously. Your readiness score updates automatically.

Install

bash

npx @mima-ai/governance-mcp@0.1.13

Or add to your MCP config (always pin the version):

json

{
  "mcpServers": {
    "mima-governance": {
      "command": "npx",
      "args": ["-y", "@mima-ai/governance-mcp@0.1.13"],
      "env": {
        "MIMA_API_KEY": "mima_ext_...",
        "MIMA_WORKSPACE_ID": "ws-..."
      }
    }
  }
}

10 tools

Tool	What it does
`get_posture`	Overall readiness score + per-framework breakdown
`list_systems`	All AI systems — registered vs unregistered
`list_evidence`	Evidence records filtered by system and time
`dry_run_attest`	Preview which controls an attestation would earn
`attest`	Write a GRC evidence record
`register_system`	Register an AI system under EU AI Act Art. 9
`acknowledge_policy`	Record a policy acknowledgment
`derive_controls`	Recommended evidence types for a system description
`check_gates`	Gate pass/fail status with exit codes
`suggest_gates`	Prioritised gate recommendations

Usage — Claude Code

Add to ~/.claude/settings.json:

json

{
  "mcpServers": {
    "mima-governance": {
      "command": "npx",
      "args": ["-y", "@mima-ai/governance-mcp"],
      "env": {
        "MIMA_API_KEY": "mima_ext_...",
        "MIMA_WORKSPACE_ID": "ws-..."
      }
    }
  }
}

Then ask Claude: "Check our compliance posture" or "Register this AI system and suggest which controls we need."

Usage — Cursor / Windsurf

Add to .cursor/mcp.json or .windsurf/mcp.json in your project root:

json

{
  "mcpServers": {
    "mima-governance": {
      "command": "npx",
      "args": ["-y", "@mima-ai/governance-mcp"],
      "env": {
        "MIMA_API_KEY": "mima_ext_...",
        "MIMA_WORKSPACE_ID": "ws-..."
      }
    }
  }
}

Dry-run support

All write tools support dry-run — preview what controls you'd earn before committing:

code

dry_run_attest({ record_type: "ai_risk_assessment", system_name: "loan-scorer" })
// → { mapped_controls: ["EUAIA_ART9", "ISO42001_6_1", "NIST_AIRF_MAP_1"] }

Four frameworks, one call

Framework	What it covers
EU AI Act	Art. 9–15 risk management, oversight, accuracy obligations
ISO 42001	AI management system controls — A.6.x risk, A.9.x performance
SOC 2	CC3.x–CC8.x risk, change, and incident management
NIST AI RMF	GOVERN, MAP, MEASURE, MANAGE functions

Get an API key

mima.works → sign up → copy your key from the dashboard.

Python SDK

For app-code attestation (decorators, batch pushes, pre-approval gates):

bash

pip install mima-governance

Docs

docs.mima.works

works.mima/governance-mcp

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

@mima-ai/governance-mcp

Install

10 tools

Usage — Claude Code

Usage — Cursor / Windsurf

Dry-run support

Four frameworks, one call

Get an API key

Python SDK

Docs

Install

Configuration

Related servers