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.

Raycast

Use your memos from Raycast AI.

MCP servers in Raycast need Raycast Pro.

Connect with the GigaRAG CLI

Raycast keeps its settings somewhere a command cannot safely rewrite, so the CLI prints exactly what to enter instead. Signing in still happens in your browser, and no key is written into any config file.

npm install -g gigarag
gigarag login
gigarag connect raycast

Paste what it prints, then restart Raycast afterwards. Nothing here expires, and gigarag connect --remove takes GigaRAG back out of everything it touched.

Sign in with GigaRAG

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

  1. 1.

    Add GigaRAG as below, but set OAuth Type to Dynamic instead of adding a header

  2. 2.

    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.

    Run the Install MCP Server command

    Name it GigaRAG and set the transport to HTTP.

  2. 2.

    Paste this as the URL

    Server URL
    https://mcp.gigarag.com/mcp
  3. 3.

    Under HTTP Headers, add Authorization with this value

    Authorization
    Bearer <api-key>
  4. 4.

    Save with Cmd+Enter

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: Model Context Protocol