Quick Start

Set BASE_DIR to the folder you want to search. Documents must live under it.

Add the MCP server to your AI coding tool:

For Cursor — Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "local-rag": {
      "command": "npx",
      "args": ["-y", "mcp-local-rag"],
      "env": {
        "BASE_DIR": "/path/to/your/documents"
      }
    }
  }
}

For Codex — Add to ~/.codex/config.toml:

[mcp_servers.local-rag]
command = "npx"
args = ["-y", "mcp-local-rag"]

[mcp_servers.local-rag.env]
BASE_DIR = "/path/to/your/documents"

For Claude Code — Run this command:

claude mcp add local-rag --scope user --env BASE_DIR=/path/to/your/documents -- npx -y mcp-local-rag

Restart your tool, then start using it:

You: "Ingest api-spec.pdf"
Assistant: Successfully ingested api-spec.pdf (47 chunks created)

You: "What does the API documentation say about authentication?"
Assistant: Based on the documentation, authentication uses OAuth 2.0 with JWT tokens.
          The flow is described in section 3.2...

That's it. No installation, no Docker, no complex setup.

Why This Exists

You want AI to search your documents—technical specs, research papers, internal docs. But most solutions send your files to external APIs.

Privacy. Your documents might contain sensitive data. This runs entirely locally.

Cost. External...