What it does
Performance Ai MCP is a Model Context Protocol (MCP) server published by csoai-org and described as part of the MEOK AI Labs ecosystem. The publisher's examples name three tools: analyze_waterfall_data, suggest_optimizations and calculate_core_web_vitals. The documentation does not describe what these tools return, so their scope is known only from their names.
It suits a developer who wants an MCP-compatible AI assistant to work with performance data, such as waterfall timings or Core Web Vitals, and to get optimisation suggestions. The publisher's examples show requests made in plain language to the assistant once the server is configured.
To run it, add the server to the configuration file of an MCP client such as Claude Desktop, or install the Python package with pip and start its command, which communicates over stdio transport.
Limitations and requirements
Requires an MCP client, such as Claude Desktop, or a Python environment with pip to run the server over stdio. Setup means editing the client's configuration file. The publisher's page also describes paid tiers and a free tier of 10 calls per day per MCP for the separate MEOK Governance Suite.
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/performance-ai-mcp
Performance Ai MCP Server by MEOK AI Labs
v1.0.8As shown on registry.modelcontextprotocol.io when we last read it