Vibe Coding Discoverjdocmunch-mcp
View on GitHubThe leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
A local-first MCP server that indexes documentation by heading and retrieves byte-precise sections for coding agents. Supports lexical BM25 search by default, optional semantic or hybrid search, and documentation health and OpenAPI tools.
Use Cases
Search technical documentation by section from a coding agentRetrieve precise documentation excerpts without loading whole filesIndex local documentation or GitHub repositoriesAssess documentation coverage, freshness, and broken linksSearch and navigate OpenAPI specifications
Built With
- Language
- Python
- Frameworks
- Model Context Protocol · FastEmbed · sentence-transformers · ONNX Runtime
Tags
documentation retrieval · section indexing · semantic search · BM25 · hybrid search · token efficiency · local-first · OpenAPI