Search and retrieve documentation using Whoosh full-text search with MCP server support
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"whoosh-rag-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Whoosh RAG MCP - Documentation Search Server A Model Context Protocol (MCP) server that provides full-text search capabilities for documentation using Whoosh. This allows AI assistants like Cline and GitHub Copilot to search and retrieve relevant documentation. ## Rationale Large language models (LLMs) are often trained on outdated code and documentation, which can lead to suggestions that use deprecated functions or patterns. This MCP server uses Whoosh for fast, precise, and explainable full-text search over your latest documentation, helping AI assistants and users find up-to-date, authoritative answers. This improves coding correctness and reliability, especially in technical environments. Whoosh is lightweight, CPU-friendly, and requires no embeddings or GPUs. For best results, include synonyms in your queries to broaden coverage. ## Features - **Full-text search** through markdown (.md, .mdx) and reStructuredText (.rst) documentation - **Section-based indexing** for granular search results - **Stemming analyzer** for better search matches - **Multiple search modes**: snippets, full content, or by section ## Tools Provided The MCP server exposes the following tools to AI assistants: 1. **`search_documentation`** - Search indexed documentation with full-text search 2. **`build_documentation_index`** - Build/rebuild the search index from documentation files 3. **`update_documentation_index`** - Update the existing index (currently performs full rebuild) 4. **`get_index_info`** - Get information about the current index status ## Installation ### 1. Install from PyPI The easiest way to install the package is from PyPI: ```bash pip install whoosh-rag-mcp ``` Alternatively, you can install directly from GitHub: ```bash pip install git+https://github.com/jianlins/whoosh_rag_mcp.git ``` Or for development (editable install): ```bash git clone https://github.com/jianlins/whoosh_rag_mcp.git cd whoosh_rag_mcp pip install -e . ``` ### 2. Configure Envir…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.