Back to GigaRAG

Connect an agent

Give an AI tool access to your GigaRAG Workspace, so it can search, read and write your memos while it works.

Junie

JetBrains' coding agent, in the IDE or the terminal. In JetBrains IDEs, use Junie or the Copilot plugin: AI Assistant does not document keys or sign-in for remote servers.

Connect with the GigaRAG CLI

One command connects Junie and every other AI tool on this machine. Signing in happens in your browser, so no key is written into any config file.

npm install -g gigarag
gigarag login
gigarag connect

Restart Junie afterwards. Nothing here expires, and gigarag connect --remove takes GigaRAG back out of everything it touched.

Sign in with GigaRAG

Connect without a key: Junie opens your browser, you sign in to GigaRAG and pick this workspace.

  1. 1.

    Add GigaRAG without a header

    ~/.junie/mcp/mcp.json
    {
  "mcpServers": {
    "gigarag": { "url": "https://mcp.gigarag.com/mcp" }
  }
}
  2. 2.

    Run /mcp and authorize GigaRAG in the installation assistant

  3. 3.

    Sign in with your GigaRAG account

    Your browser opens GigaRAG. Pick the workspace to share and approve. No key is stored in the app, and the connection does not expire.

Or set it up by hand

  1. 1.

    Add GigaRAG to your user MCP config

    ~/.junie/mcp/mcp.json
    {
  "mcpServers": {
    "gigarag": {
      "url": "https://mcp.gigarag.com/mcp",
      "headers": { "Authorization": "Bearer <api-key>" }
    }
  }
}
  2. 2.

    Run /mcp to check that gigarag is connected

Check it worked

Send this once it is connected. An answer drawn from your workspace means the connection is live.

List my GigaRAG buckets.

Written from the official docs: Junie MCP configuration