# apifare for OpenAI Agents SDK

One prepaid, capped key for every API your agent needs, under hard caps and a kill switch.

1. Get a token: https://apifare.com/start?origin=page:integrations-openai-agents-sdk (shown once).
2. Connect your agent to apifare's remote MCP endpoint with MCPServerStreamableHttp. The token is read from the APIPAY_TOKEN environment variable and sent as an Authorization header.

```
pip install openai-agents
```

```
import asyncio
import os

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

async def main() -> None:
    token = os.environ["APIPAY_TOKEN"]
    async with MCPServerStreamableHttp(
        name="apifare",
        params={
            "url": "https://apifare.com/mcp",
            "headers": {"Authorization": f"Bearer {token}"},
            "timeout": 10,
        },
    ) as server:
        agent = Agent(
            name="Assistant",
            instructions="Use the MCP tools to answer the questions.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "What's the weather in London?")
        print(result.final_output)

asyncio.run(main())
```

   Set APIPAY_TOKEN and OPENAI_API_KEY, then run it. To run apifare locally instead, MCPServerStdio takes npx -y apifare-mcp with APIPAY_TOKEN in its env.
3. Try it: "search the web for X", then "fetch a URL", then "what's the weather in London".
4. Caps and the kill switch are checked before dispatch. An empty balance returns HTTP 402 with a top-up link (see /errors.md).

Prices: https://apifare.com/capabilities. Config checked against https://openai.github.io/openai-agents-python/mcp/ on 2026-09-13.