Dense Knowledge is a Model Context Protocol (MCP) server: Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval. In practice that means any MCP-compatible AI assistant can call Dense Knowledge's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the Python package dense-knowledge-mcp (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v1.2.0, published under the MIT license, with source at Lucky44k/dense-knowledge-mcp on GitHub.
Dense Knowledge is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Dense Knowledge for Lucky44k, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
▸PyPI package — dense-knowledge-mcp · MCP over stdio
▸Open source — MIT license · Lucky44k/dense-knowledge-mcp