Connect an agent

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

OpenAI Agents SDK

Give agents built on the OpenAI Agents SDK 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.

1.
Install the SDK
```
pip install openai-agents
```

Add GigaRAG to the agent

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp


async def main():
    async with MCPServerStreamableHttp(
        name="gigarag",
        params={
            "url": "https://mcp.gigarag.com/mcp",
            "headers": {"Authorization": "Bearer <api-key>"},
        },
    ) as gigarag:
        agent = Agent(name="Assistant", mcp_servers=[gigarag])
        result = await Runner.run(agent, "List my GigaRAG buckets.")
        print(result.final_output)


asyncio.run(main())

Check it worked

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

Run it. The model should answer with your GigaRAG buckets.

Written from the official docs: MCP in the Agents SDK