Analyze your MCP server setup to identify token costs, performance grades, duplicate tools, and optimization opportunities. Built for developers managing multiple MCP servers who need visibility into resource usage and configuration efficiency.
io.github.yifanyifan897645/mcp-checkup
Local install
STDIO
No auth required
How models use it and what it is built for.
Analyze your MCP server setup to identify token costs, performance grades, duplicate tools, and optimization opportunities. Built for developers managing multiple MCP servers who need visibility into resource usage and configuration efficiency.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Yifanyifan897645 MCP Checkup.
Paste any of these into Agent Studio after connecting Yifanyifan897645 MCP Checkup.
Common questions about connecting and running Yifanyifan897645 MCP Checkup.
What does mcp-checkup actually analyze?
It audits your MCP server configuration to calculate token costs, assign performance grades, detect duplicate tools across servers, and provide optimization recommendations. This helps you understand resource usage and streamline your setup.
How do I install and run mcp-checkup?
Install via `npx mcp-checkup@0.1.0`. It communicates over stdio, so it integrates directly into your MCP environment. Refer to the project repository for detailed setup instructions.
Can mcp-checkup help reduce my token usage?
Yes—by identifying duplicate tools and inefficient configurations, you can consolidate servers and remove redundant capabilities, directly lowering token consumption across your MCP setup.
Does mcp-checkup work with all MCP servers?
It analyzes any MCP servers in your environment. Check the repository for compatibility notes and any specific configuration requirements for your server types.
What's the difference between a grade and optimization tips?
Grades rate your overall MCP configuration health, while optimization tips are specific, actionable recommendations—like removing duplicates or consolidating low-value servers—to improve performance and reduce costs.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio