qmd Knowledge-Base MCP Server

Example Use Cases

• 1

  Perform full-text and semantic search over local markdown document collections.

• 2

  That require integration with a local MCP server to retrieve and index documents efficiently.

• 3

  Leverage hybrid search combining BM25, vector embeddings, and LLM query expansion.

Description

qmd is a local knowledge-base search engine designed for markdown files, featuring BM25 full-text search, vector semantic search, and hybrid search with LLM query expansion. It offers a single binary with minimal dependencies and supports integration with AI agents via a JSON-RPC 2.0 MCP server over stdio or HTTP. The server enables efficient document retrieval, indexing, and semantic search, making it ideal for personal or work knowledge management.