sphinxcontrib-mcp
Integrates Meilisearch as a search backend, allowing agents to perform full-text searches across the documentation using Meilisearch's search capabilities.
Provides tools for interacting with a built Sphinx documentation site, including retrieving page context, navigation structure, metadata, and performing native searches.
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., "@sphinxcontrib-mcpSearch for 'troubleshooting' and show the page context"
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.
sphinxcontrib-mcp
A FastMCP server that exposes a built Sphinx site's navigation, page context,
metadata, and search tools. It reads the webmcp.json manifest emitted by
sphinxcontrib-webmcp, so the server and browser-side WebMCP integration share
one public schema.
Run
sphinx-mcp --manifest docs/_build/html/webmcp.jsonThe default transport is stdio. Use --transport http --host 127.0.0.1 --port 8001 for Streamable HTTP.
Related MCP server: mdbook-mcp-server
Tools
sphinx.get_page_context: return page title, URL, source, headings, and children.sphinx.list_navigation: return the Sphinx root and resolved children.sphinx.get_documentation_metadata: return public build, search, and schema metadata.sphinx.search: search native Sphinx references or configured docindex backends.sphinx.navigate: resolve a same-site page without performing browser navigation.
native, docindex, oxirs, and meilisearch search modes remain distinct.
The server only uses public_api_key; administrative Meilisearch keys are not
accepted from the manifest. Search results from OxiRS and Meilisearch are
returned under separate backend entries.
This server cannot be deployed
Maintenance
Related MCP Connectors
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
Query any docs site via MCP. Submit a URL, ask questions, get cited answers.
Search API for Google, Bing, Amazon, Maps, DuckDuckGo, Yelp, and TripAdvisor, exposed as MCP tools.
1
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceIndexes documentation sites by base URL and serves keyword search, optional semantic search, and Markdown page retrieval as MCP tools, all from a single SQLite file.-
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to access and read mdbook documentation, including structure, content, and search.3 npm3MIT
- FlicenseAqualityDmaintenanceEnables searching documentation from GitHub repositories and web pages via MCP tools, with in-memory indexing and caching for fast retrieval.3-
- AlicenseNot gradedqualityAmaintenanceEnables searching, reading, and navigating MkDocs documentation sites through MCP tools for keyword, semantic, or hybrid search, document browsing, and project metadata.1BSD 2-Clause "Simplified"