What it does
The server provides tools for AI and ML model risk management in banking, referencing Basel III, SR 11-7 and ECB TRIM. The publisher's documentation names three tools: model_risk_tier, validation_requirements and ecb_trim_check. It also states that the server is built with EU AI Act compliance features covering Articles 9, 13, 15, 26 and 50.
The publisher describes it as intended for banks deploying AI in credit. It suits teams that need to assess model risk tiers, identify validation requirements or check against ECB TRIM expectations.
It runs as a stdio server, added to an MCP client configuration such as Claude Desktop, or installed as a Python package. The free tier is MIT-licensed and needs no API key. Signed compliance attestations and unlimited audits are available through a paid subscription.
Limitations and requirements
The free tier is limited to 10 calls per day. Signed attestations and unlimited audits require a paid subscription. The server must be configured in an MCP client such as Claude Desktop or run as a stdio process.
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/basel-ai-overlay-mcp
Basel III + SR 11-7 + ECB TRIM AI/ML model risk management for banks deploying AI in credit, cap...
v1.0.10As shown on registry.modelcontextprotocol.io when we last read it