Gnosis Mcp
Description
Zero-config knowledge base for AI coding agents. Loads your markdown docs into a searchable database and exposes them as MCP tools — search, read, and manage documentation without leaving your editor. Works instantly with SQLite (no setup), upgrades to PostgreSQL + pgvector for…
About
Zero-config knowledge base for AI coding agents. Loads your markdown docs into a searchable database and exposes them as MCP tools — search, read, and manage documentation without leaving your editor. Works instantly with SQLite (no setup), upgrades to PostgreSQL + pgvector for hybrid semantic search. Includes skills…
Details
- Author
- nicholasglazer
- GitHub stars
- 25
- Downloads
- 150
- Categories
- Search, Knowledge Base, Other
Jump to
- 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+)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Gnosis McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"gnosis mcp": {
"gnosis": {
"command": "gnosis-mcp",
"args": [
"serve"
]
}
}
}
}McpServers
{
"gnosis": {
"command": "gnosis-mcp",
"args": [
"serve"
]
}
}What makes gnosis-mcp different
- Your data stays on your machine. SQLite by default, PostgreSQL at scale — nothing leaves the host.
- Index anything that's docs-shaped. Markdown, git commit history, crawled websites — one index, one search API.
- Measured, not marketed. Ships BEIR SciFact numbers (0.671 nDCG@10 — within 1 % of the Lucene BM25 baseline), a reproducible eval harness (gnosis-mcp eval), and a chunk-size sweep showing where the quality plateau actually sits.
Full side-by-side vs Context7 / docs-mcp-server / mcp-local-rag: gnosismcp.com#compare.
---
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
