Darwin RAG

Overview

Darwin RAG is a Model Context Protocol (MCP) server: Local-first RAG engine with MCP server for AI agent integration. In practice that means any MCP-compatible AI assistant can call Darwin RAG's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package darwin-rag (via uvx) speaks MCP over stdio on your machine. The current release is v0.2.18, with source at Brightdotdev/DARWIN on GitHub.

Darwin RAG 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 Darwin RAG for Brightdotdev, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "darwin_rag": {
      "command": "uvx",
      "args": [
        "darwin-rag"
      ]
    }
  }
}