Local Documentation MCP Server with RAG
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":"mcp-local-context","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.
# MCP Local Context A simple MCP server for local documentation with RAG capabilities. This package provides a simple command to install and use the MCP server for Cursor and Claude that can take a list of folders as sources. [](https://badge.fury.io/py/mcp-local-context) [](https://pypi.org/project/mcp-local-context/) [](https://opensource.org/licenses/MIT) This MCP (Model-Context-Protocol) server provides access to local documents stored in source folders, making it easy for AI assistants to access your library documents. ## Features - **Local Document Access**: Serves document files from your local source folders - **Multiple Source Folders**: Configure multiple source directories for your documents - **Document Type Classification**: Automatically categorizes documents as documentation, guides, or conventions - **Type-Based Filtering**: Search and retrieve documents by specific type - **Semantic Search**: Find documents based on meaning, not just keywords - **RAG Implementation**: Uses vector embeddings for document similarity and relevance ranking - **Directory Listing**: List all available document files - **Works Offline**: No external API calls - everything is served locally ## Installation ### Requirements - Python 3.10+ - An MCP-compatible client (Cursor, Claude Desktop, etc.) ### Using pip (recommended) ```bash # Install from PyPI pip install mcp-local-context # Run the server mcp-local-context ``` To install with RAG capabilities (recommended for semantic search): ```bash pip install "mcp-local-context[rag]" ``` Or install directly from GitHub: ```bash pip install git+https://github.com/steedmonteiro/mcp-local-context.git ``` ### Document Organization Prepare your document files (Markdown, MDX, and text files are supported) and o…
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.