What it does
The server is an MCP server from MEOK AI Labs for producing AI explainability and transparency reports. Its documented example tools are quick_scan, generate_model_card and explain_decision. The README says the server covers EU AI Act provisions, including Articles 9, 13, 15, 26 and 50, with some marked as applicable only in certain cases. It does not state that using it makes a system compliant.
A developer would reach for it when building an AI system that needs transparency documentation, model cards or explanations of individual decisions, and who wants these available as tools inside an MCP-compatible assistant.
To run it, install the Python package explainability-report-mcp with pip and start the explainability-report-mcp command, which uses stdio transport. Alternatively, add the server to the claude_desktop_config.json file for Claude Desktop or to the configuration of another MCP client. The examples show the tools being called from the assistant with a natural-language request.
Limitations and requirements
The README mentions paid MEOK plans and a free tier limited to 10 calls per day per MCP across the wider MEOK suite. It does not state usage limits for this server on its own. The server needs an MCP-compatible client, such as Claude Desktop, or a Python installation with pip.
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/explainability-report-mcp
Explainability Report MCP Server by MEOK AI Labs
v1.0.16As shown on registry.modelcontextprotocol.io when we last read it