mcp-taro-docs
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-taro-docs query Taro docs for cover-image component"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-taro-docs
An MCP (Model Context Protocol) server for Taro official docs (https://docs.taro.zone).
It exposes a 2-step retrieval workflow:
Query candidates from the docs sitemap (query)
Fetch full page content by
asset_id(get)
Tools
taro-official-query-assets
Filters and ranks candidate doc pages from https://docs.taro.zone/sitemap.xml (URL matching + lightweight scoring).
Arguments:
query(required): Query stringtop_k(optional, default 10, max 50): Maximum number of candidates to returnpathPrefix(optional): Path prefix to narrow the search scope, e.g./docs/componentscaseSensitive(optional, default false): Whether to use case-sensitive matching
Returns:
results[]: items includeasset_id,url,file_path,score, etc.
taro-official-get-assets
Fetches the full doc page text by asset_id.
Arguments:
asset_ids(required):asset_idlist returned bytaro-official-query-assets(max 10)
Returns:
contents[]: items includetitle,url,file_path,content(plain text), etc.
Related MCP server: web-docs-mcp
Local build & run
Requires: Node.js >= 18
cd /Users/bytedance/Downloads/taro-docs/mcp-taro-docs
npm install
npm run buildBuild output:
dist/index.cjs(CommonJS, usable as the MCP Server entrypoint)
Quick test (stdio JSON-RPC)
1) List tools
node dist/index.cjs <<'EOF'
{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}
EOF2) Query then get (CoverImage example)
node dist/index.cjs <<'EOF'
{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"taro-official-query-assets","arguments":{"query":"cover-image","top_k":5,"pathPrefix":"/docs/components"}}}
EOFCopy results[0].asset_id from the output, then call get:
node dist/index.cjs <<'EOF'
{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"taro-official-get-assets","arguments":{"asset_ids":["<asset_id>"]}}}
EOFMCP client config examples
Cursor (mcp.json)
{
"Taro Official Docs": {
"command": "node",
"args": ["/Users/bytedance/Downloads/taro-docs/mcp-taro-docs/dist/index.cjs"]
}
}Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"taro-official-docs": {
"command": "node",
"args": ["/Users/bytedance/Downloads/taro-docs/mcp-taro-docs/dist/index.cjs"]
}
}
}Notes
asset_idis a stable hash of the page URL (same URL => sameasset_id)pathPrefixis a scope filter; it does not need to equal the full pathThe sitemap is cached in-memory per process (restart to refresh)
Available Tools
2 toolstaro-official-get-assetsA
Fetch online official docs page content by asset_ids returned from taro-official-query-assets.
Inputs: asset_ids (required).
taro-official-query-assetsA
Query Taro official online docs (docs.taro.zone) via sitemap URL matching. Returns asset_ids for taro-official-get-assets.
Inputs: query (required), top_k, pathPrefix, caseSensitive.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one finds asset IDs via sitemap matching, the other fetches content using those IDs. No overlap or confusion between them.
Both tool names follow the same verb-noun pattern with a consistent 'taro-official-' prefix, making the interface predictable and uniform.
With only two tools, the server feels minimal but is arguably sufficient for its narrow scope of querying and fetching docs. It borders on being too thin for a full-featured docs server.
The query-then-get workflow is logically complete for retrieving specific doc pages. Minor gaps exist, such as no direct URL fetch or list-all capability, but the core task is well covered.
Maintenance
Related MCP Connectors
MCP server for querying Forkast documentation
MCP server for opencode documentation, generated by doc2mcp.
MCP server for stocksense-ai documentation, generated by doc2mcp.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that serves documentation and enables AI-powered search, Q\&A, and document analysis for developer tools and guides.54MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for searching web documentation via sitemap.xml, enabling semantic search across multiple documentation sites using Ollama embeddings.MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for documentation search that automatically indexes web documentation sites and provides semantic, full-text, or hybrid search capabilities.2 npmMIT
- FlicenseAqualityCmaintenanceA search-and-retrieve MCP server that queries official documentation sites for modern libraries like LangChain, OpenAI, and Docker, extracting clean text content using Google Serper API and trafilatura.1-