{
  "markdown": "# @governmyai/mcp-server\n\nGovernMy.ai MCP server — query AI governance obligations from Claude Desktop, Cursor, or any MCP-compatible client.\n\nCovers EU AI Act, ISO 42001, Colorado AI Act, NIST AI RMF, HIPAA (AI provisions), SOX (AI provisions), and FTC AI guidance.\n\n## What this does\n\nThis MCP server gives an AI assistant (like Claude) the ability to query GovernMy's rules engine directly while you're working. You can ask questions like:\n\n- *\"What EU AI Act obligations apply if I build a hiring AI for the EU?\"*\n- *\"Which frameworks does this cover?\"*\n- *\"What evidence do I need for EU AI Act Article 10 data governance?\"*\n- *\"Does my ISO 42001 Clause 6 work also cover any NIST AI RMF functions?\"*\n\n...and get structured regulatory obligations back as part of the conversation.\n\n**Important:** this tool returns **obligations**, not verdicts. It never tells you \"you're compliant\" or \"you're not compliant\" — those are determinations only a human reviewer can make. Every response includes a `humanReviewRequired` flag where applicable.\n\n## Copy-paste into Claude\n\nAfter installing + restarting, try one of these:\n\n- *\"What are the mandatory-review obligations for a high-risk hiring AI deployed in the EU?\"*\n- *\"Show me the evidence requirements for EU AI Act Articles 11 and 14.\"*\n- *\"Compare EU AI Act and Colorado AI Act obligations for a credit-scoring AI.\"*\n- *\"Does my HR chatbot trigger any regulatory obligations? It does resume screening.\"*\n- *\"What ISO 42001 Annex A controls do I need for a generative AI system?\"*\n- *\"Which NIST AI RMF dimensions does EU AI Act Art. 10 data governance also satisfy?\"*\n- *\"I'm building a medical imaging AI — what obligations apply under HIPAA AI provisions?\"*\n- *\"List every obligation flagged as `cannotBeAutoSatisfied` across all frameworks.\"*\n\n## Install + configure (Claude Desktop)\n\n1. Register for an API key at https://governmy.ai/developers (free tier available)\n2. Open your Claude Desktop config file:\n   - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\n   - Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n3. Add the GovernMy server to your `mcpServers` object:\n\n```json\n{\n  \"mcpServers\": {\n    \"governmy\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@governmyai/mcp-server\"],\n      \"env\": {\n        \"GOVERNMY_API_KEY\": \"ooa_live_your_key_here\"\n      }\n    }\n  }\n}\n```\n\n4. Restart Claude Desktop. Ask Claude: *\"What governance frameworks does GovernMy cover?\"* — it should call the `list_frameworks` tool.\n\n## Install + configure (Cursor)\n\nAdd the server to your Cursor MCP settings (Settings → MCP Servers):\n\n- Command: `npx`\n- Args: `-y @governmyai/mcp-server`\n- Environment: `GOVERNMY_API_KEY=ooa_live_your_key_here`\n\n## Configure (other MCP clients)\n\nAny client that speaks stdio MCP can run this server. Set `GOVERNMY_API_KEY` in the client's env for the server process.\n\n## Environment variables\n\n| Variable | Required | Default | Purpose |\n|---|---|---|---|\n| `GOVERNMY_API_KEY` | yes | — | Your GovernMy.ai API key |\n| `GOVERNMY_API_URL` | no | `https://api.governmy.ai` | Override API base URL (for local dev) |\n\n## Tools exposed\n\n- **`get_obligations`** — query obligations that apply to an AI system given context (risk tier, role, industry, etc.)\n- **`classify_risk_tier`** — classify an AI system's EU AI Act risk tier (unacceptable / high / limited / minimal)\n- **`list_frameworks`** — list the frameworks the engine covers with metadata\n- **`get_rule`** — fetch the full payload for a single obligation by id\n- **`get_evidence_requirements`** — fetch required evidence artifacts for a set of obligations\n- **`get_cross_references`** — fetch cross-framework mappings for an obligation\n\nEvery tool response includes a `notAVerdict` notice reminding the AI assistant that obligations are not compliance verdicts.\n\n## What this is not\n\n- **Not legal advice.** The rules engine is a research tool + workflow accelerator. Compliance decisions require qualified human review.\n- **Not a replacement for a compliance professional.** If your AI system is materially exposed to any of the covered frameworks, pair this with a real compliance program.\n- **Not a verdict engine.** We deliberately do not return \"compliant: true\" or \"allowed: true\". This is both an ethical line and a legal one (EU AI Act Art. 14).\n\n## Support\n\n- Docs: https://docs.governmy.ai/mcp\n- API reference: https://docs.governmy.ai/api\n- Issues: https://github.com/governmyai/mcp-server/issues\n- Email: hello@governmy.ai\n\n## License\n\nMIT\n",
  "bytes": 4518,
  "sha": "68d864fd25a9ae542eca27041e60135b7bf45a081fc480cbcf3da60caff5018d",
  "repo_slug": "governmyai/mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_governmyai_mcp_server_f2f57282/readme"
}