search_docsLABSCO SUMMARY
The exclude patterns are what make the index worth searching.
Most of the hallucination problem with framework APIs is version mixing, and the crawler config is where you fix it — excluding the versioned archive paths means the local copy only contains the version you actually use. Everything is served from disk after that, so search is fast and works offline, at the cost of a crawl you re-run when the docs move on.
What it is
A Node MCP server that serves framework documentation you have crawled into local JSON files. A bundled multi-threaded crawler fetches the official docs site; the server then answers search and detail queries from that local copy.
What you get
search_docs— keyword search across the loaded documentation, optionally scoped to one source, with a result limitget_doc_detail— the full content of one page by its id, optionally scoped to a source- A crawler configured per documentation site, with include and exclude patterns so you take the component pages and skip the version archives
- Automatic detection of the JSON files in the docs directory at startup, and a reload triggered from inside a search
- Several documentation sources side by side, each addressable by name
Requirements
Node and npm. Write a source config listing each docs site with its include and exclude patterns, run the crawl, then point your client's command at the server file by absolute path. The crawler drives a browser through Puppeteer — set PUPPETEER_SKIP_DOWNLOAD if you already have Chrome installed and would rather it used yours.
Setup effort
Build from source — git clone https://github.com/ruan11223344/McpDocServer
USE CASES
01
Stopping an assistant inventing framework APIs
Have it search the crawled documentation for the method signature before it writes the call.
02
Keeping one version's docs and no others
Exclude the versioned paths in the crawler config so the index cannot mix releases.
03
Reading the page an answer came from
Fetch the full document by id after the search points at it.
04
Working with several libraries at once
Crawl each into its own source and scope a search to the one you mean.
2 tools
Listed in project docs. Your client may show a different list.
get_doc_detailBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
node on PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/ruan11223344/McpDocServer
cd McpDocServer
npm installCreate config/doc-sources.js listing each documentation site with its include and exclude patterns — config/doc-sources.js.example in the repository shows the format
TERMINAL
npm run crawlThen point Cursor at server.js by its full absolute path — <YOUR_PATH_TO_MCP_DOC_SERVER>/server.js in the block under MCP Clients
MCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"docs-mcp-server": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MCP_DOC_SERVER>/server.js"
],
"env": {
"NODE_ENV": "development"
}
}
}
}
