What it does
The server offers tools for creating and maintaining an AI risk register aligned with the NIST AI RMF. Its documented tools are assess_risk, create_risk_register and add_risk. The register covers risk scoring, treatments and controls, and keeps a signed evidence trail. The publisher's documentation also describes support for several EU AI Act articles (9, 13, 15, 26 and 50).
It suits teams that need to document and track risks in AI systems and want to work with that register through an MCP-compatible assistant, which can call the tools with plain-language requests.
The package is distributed on pip and runs over stdio transport. It is set up by adding it to an MCP client configuration, such as claude_desktop_config.json for Claude Desktop, after which the assistant can use its tools.
Limitations and requirements
Requires an MCP-compatible client, such as Claude Desktop, and a Python-based pip installation. The publisher's pricing tiers and call limits refer to the wider MEOK AI Labs governance suite and are not stated as conditions of this server.
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/risk-assessment-ai-mcp
Risk Assessment Ai MCP Server by MEOK AI Labs
v1.0.12As shown on registry.modelcontextprotocol.io when we last read it