Skip to content
MCP server

AI Governance Engineer

Read-only MCP server giving AI assistants sourced AI governance reference material

Install
Pricing
Open source
Platforms
API, CLI, vscode
Runs
Remotely
Version
0.6.1
Listing updated
today

Similar MCP servers

About AI Governance Engineer

AI Governance Engineer is an open-source MCP server for compliance and regulation. It runs as a hosted remote server, so there is nothing to install locally.

The server sits in front of the open data API of a governance reference site and exposes its obligation register, crosswalk between frameworks, glossary, engineering patterns, templates and draft control specifications as MCP tools. Each answer names the source page, dataset and version it was read from, so a question about the EU AI Act or ISO/IEC 42001 comes back with a citable reference rather than free-form text.

It is a remote Streamable HTTP endpoint with no account or API key. The README says it keeps no data of its own, caches upstream documents in memory and does not log client addresses or the content of requests. Clients such as Claude, Claude Code, Cursor and VS Code can connect by pasting the endpoint URL, and the README includes configuration snippets for each.

The material is aimed at compliance, governance and AI engineering practitioners who want quick lookups inside their assistant. The publisher states that mappings and obligation rows are illustrative, not legal advice, and that users should check the primary source before relying on them. The content is licensed CC BY 4.0.

Install

Run in a terminal

claude mcp add --transport http reference https://mcp.aigovernanceengineer.com/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.aigovernanceengineer.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "reference": {
      "url": "https://mcp.aigovernanceengineer.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "reference": {
      "type": "http",
      "url": "https://mcp.aigovernanceengineer.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "reference": {
      "serverUrl": "https://mcp.aigovernanceengineer.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "reference": {
      "type": "http",
      "url": "https://mcp.aigovernanceengineer.com/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (12)

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

search_bok
Searches chapters, sections and pattern pages of the Body of Knowledge.
get_obligations
Filters rows of the obligation register.
get_obligation
Returns one obligation by its id.
map_clause
Finds clauses of other frameworks on the same topic as a given clause.
search_glossary
Searches glossary terms by name or definition.
get_term
Returns one glossary term with its definition and related terms.
list_patterns
Lists engineering patterns, optionally for one stack layer.
get_pattern
Returns one pattern in full.
list_controls
Lists reference controls from the open control profiles.
get_control
Returns one draft control specification.
list_templates
Lists the templates and JSON Schemas library.
get_template
Returns one template or schema with its file content.

What it does

Sourced obligation lookups
Filters an obligation register by framework, role, system class, status, layer or date, returning rows with stable ids.
Cross-framework clause mapping
Shows clauses from other frameworks that cover the same topic as a given clause, with strength and verification flags.
Glossary and term pages
Searches governance terms and returns definitions, sources and the chapters that use each term.
Engineering pattern access
Lists and retrieves named engineering patterns, optionally filtered by stack layer.
Templates and schemas
Retrieves JSON Schemas, filled examples and human templates from the template library.
Draft control specifications
Searches and reads reference control specifications with objectives, verification and evidence fields.

Good for

  • Asking an assistant which obligations apply to a deployer of a high-risk system before a given date
  • Comparing how an EU AI Act article maps to ISO/IEC 42001 or NIST AI RMF clauses
  • Looking up the definition and source of a regulatory term while drafting a policy
  • Retrieving an incident record schema or impact assessment template for a project
  • Finding engineering patterns for a given layer of an AI system stack

Pricing

Open source

Free public endpoint; source code is published in the repository.

Prices change. Check aigovernanceengineer.com before you buy.

AI Governance Engineer FAQ

Does the server require an account or API key?

No. The README says the public endpoint uses Streamable HTTP with no authentication, and no account or key is needed.

Is the data stored or logged?

The README says the server holds no data of its own, does not log client IP addresses, user agents or request arguments, and reads from the public API with an in-memory cache.

What license applies to the returned data?

The README and page state the data is the Body of Knowledge licensed under CC BY 4.0, with attribution to Jorge García Aibar.

Can I connect it to Claude?

Yes. The page describes adding the endpoint as a custom connector in Claude web and desktop, and using claude mcp add with the HTTP transport in Claude Code.

Is AI Governance Engineer free?

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

How do I add AI Governance Engineer to Claude Code?

Run this command in your terminal: claude mcp add --transport http reference https://mcp.aigovernanceengineer.com/mcp

What are the best alternatives to AI Governance Engineer?

The closest alternatives to AI Governance Engineer are AI Adoption Controls Framework (AACF) and Iso 27001 Ai MCP.

Where this comes from

  • Description: written from the project's README, the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers