# apifare for LlamaIndex

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-llamaindex (shown once).
2. Connect with BasicMCPClient, which sends your token as an Authorization header, and turn the server's tools into LlamaIndex tools with McpToolSpec.

```
pip install llama-index-tools-mcp llama-index-llms-openai
```

```
import asyncio, os
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

async def main():
    client = BasicMCPClient(
        "https://apifare.com/mcp",
        headers={"Authorization": f"Bearer {os.environ['APIPAY_TOKEN']}"},
    )
    tools = await McpToolSpec(client=client).to_tool_list_async()
    agent = FunctionAgent(
        name="Agent",
        description="Agent with apifare tools",
        llm=OpenAI(model="gpt-4o"),
        tools=tools,
        system_prompt="You are a helpful assistant.",
    )
    print(await agent.run("What's the weather in London?"))

asyncio.run(main())
```

   Set APIPAY_TOKEN and OPENAI_API_KEY, then run it. For a local server instead, BasicMCPClient("npx", args=["-y", "apifare-mcp"], env={...}) takes the same token.
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://developers.llamaindex.ai/python/framework-api-reference/tools/mcp/ on 2026-09-13.