What it does
This MCP server provides tools based on the NIST AI Risk Management Framework, organised around its MAP, MEASURE, MANAGE and GOVERN functions. It includes a risk register and a trustworthy AI assessment. The documented tools include assess_risk_profile, map_ai_impact and generate_risk_controls, which an assistant can call with a natural-language request.
Someone building an AI system might reach for it to structure risk assessment work or to draft risk controls. The publisher's documentation says the server covers EU AI Act Articles 9, 13 and 15, and covers Articles 26 and 50 where applicable. The publisher also lists related MCP servers in the same fleet, including meok-eu-aia-art-9-rms-mcp and risk-assessment-ai-mcp.
To run it, add the server to an MCP client configuration, such as the claude_desktop_config.json file used by Claude Desktop. The server communicates over stdio transport. The code is published under the MIT licence by CSOAI-ORG and MEOK AI Labs.
Limitations and requirements
Requires an MCP client, such as Claude Desktop, with the server added to its configuration file. Runs over stdio transport.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/nist-rmf-ai-mcp
Nist Rmf Ai MCP Server by MEOK AI Labs
v1.0.16As shown on registry.modelcontextprotocol.io when we last read it