Darwin RAG for VS Code

io.github.brightdotdev/darwin-rag

Local-first RAG engine with MCP server for AI agent integration.

client:VS Code transport:stdio runtime:pypi

Install Darwin RAG in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "openai-api-key",
      "description": "OPENAI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "anthropic-api-key",
      "description": "ANTHROPIC_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-api-key",
      "description": "GEMINI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "darwin-base-dir",
      "description": "DARWIN_BASE_DIR",
      "password": true
    }
  ],
  "servers": {
    "darwin-rag": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "darwin-rag"
      ],
      "env": {
        "OPENAI_API_KEY": "${input:openai-api-key}",
        "ANTHROPIC_API_KEY": "${input:anthropic-api-key}",
        "GEMINI_API_KEY": "${input:gemini-api-key}",
        "DARWIN_BASE_DIR": "${input:darwin-base-dir}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

Darwin RAG in other clients

Darwin RAG MCP server