Gnosis Mcp

What is Gnosis MCP?

Gnosis MCP is a Model Context Protocol server that lets AI coding assistants search your local documentation instead of pasting entire files into context. It indexes local files, git commit history, and crawled websites into a local database, then provides ranked, highlighted snippets via search_docs — typically 300–800 tokens per lookup. It is designed for developers using AI agents who want to reduce token usage (5–10× fewer tokens per lookup) and keep data local (SQLite by default, no cloud dependencies).

How to use Gnosis MCP?

Install via pip install gnosis-mcp, then run gnosis-mcp ingest ./docs/ to load documents into SQLite and gnosis-mcp serve to start the MCP server. Connect your editor (Claude Code, Cursor, Windsurf, VS Code, JetBrains, Cline) by adding the server configuration (e.g., "command": "gnosis-mcp", "args": ["serve"]). Optional extras include gnosis-mcp[embeddings] for hybrid semantic+keyword search and gnosis-mcp[web] for crawling websites. To run with Docker, use docker run -p 8000:8000 -v "$PWD/docs:/docs:ro" -v gnosis-data:/data ghcr.io/nicholasglazer/gnosis-mcp:latest.

Key features of Gnosis MCP

• Zero‑config setup with SQLite by default (pip install and go)
• Hybrid search combining BM25 keyword + local ONNX embeddings (no API key)
• Cross‑encoder reranking optional (off by default; test before enabling)
• Ingest git commit history as searchable context (ingest-git)
• Web crawl from any website via sitemap or link crawl (crawl)
• Multi‑format support: .md, .txt, .ipynb, .toml, .csv, .json, .rst, .pdf
• Auto‑linking via relates_to frontmatter for navigable document graph
• Watch mode, prune (delete stale chunks), and wipe for full re‑ingest
• Built‑in eval harness (gnosis-mcp eval) for Hit@K, MRR, Precision@K
• PostgreSQL backend (pgvector + tsvector) ready for larger scale
• REST API alongside MCP on the same port (v0.10.0+)

Use cases of Gnosis MCP

• AI coding assistant referencing local