Analyze Rspack build performance and get optimization recommendations through an MCP server. For developers optimizing build times and bundle size in Rspack projects.
io.github.yifancong/rsdoctor
Local install
STDIO
No auth required
How models use it and what it is built for.
Analyze Rspack build performance and get optimization recommendations through an MCP server. For developers optimizing build times and bundle size in Rspack projects.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Yifancong Rsdoctor.
Paste any of these into Agent Studio after connecting Yifancong Rsdoctor.
Common questions about connecting and running Yifancong Rsdoctor.
What does the Rsdoctor MCP server do?
It integrates Rspack build analysis into your AI chat, providing performance metrics, bundle composition, and optimization recommendations. You can query build data and get actionable insights without leaving your development environment.
Does this work with any Rspack project?
Yes, it's designed for Rspack projects. The server analyzes build artifacts and provides recommendations specific to Rspack's bundling behavior and configuration.
How do I install and set up the Rsdoctor MCP server?
Install via npm with `npx @rsdoctor/mcp-server@0.1.2-beta.0`. The server runs over stdio transport, so configure it in your MCP client (like Claude Desktop) to connect to your Rspack project.
Is this a beta product?
Yes, the current version is 0.1.2-beta.0. Expect ongoing improvements and potential breaking changes. Report issues and feedback to help stabilize the tool.
What kind of build analysis can I get?
The server provides build performance metrics, module-level analysis, bundle size breakdown, and optimization recommendations. Exact capabilities depend on the build data your Rspack project generates.
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