Connect an agent

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

Letta

Give stateful Letta agents access to your memos.

Use it in code

The snippet has your key in it so it runs as pasted. Move it to an environment variable before the code is committed or shared.

client is the Letta client your code already creates.

client.mcp_servers.create(
    server_name="gigarag",
    config={
        "mcp_server_type": "streamable_http",
        "server_url": "https://mcp.gigarag.com/mcp",
        "auth_header": "Authorization",
        "auth_token": "Bearer <api-key>",
    },
)

Check it worked

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

Attach the GigaRAG tools to an agent and ask it to list your buckets.

Written from the official docs: Remote MCP servers