LlamaIndex

McpToolSpec, into an agent or a workflow.

Setup

1. pip install llama-index-tools-mcp
2. Point a BasicMCPClient at the endpoint with your key as a header.
3. Wrap it in McpToolSpec and hand the tools to an agent.

import os, asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.anthropic import Anthropic

async def main():
    client = BasicMCPClient(
        "https://api.unzoi.com/mcp",
        headers={"x-api-key": os.environ["UNZOI_KEY"]},
    )
    tools = await McpToolSpec(client=client).to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=Anthropic(model="claude-sonnet-5"),
        system_prompt="Use unzoi for current events. Prefer list_stories when the question is about an event.",
    )
    print(await agent.run("Summarise this week's semiconductor policy coverage."))

asyncio.run(main())

What differs here

• McpToolSpec can be restricted to a subset with allowed_tools, which is worth doing — a research agent has no use for account_status.
• Use the async tool list. The sync variant blocks the event loop, which matters inside a workflow.
• The tools are ordinary FunctionTools once converted, so they compose with everything else in a LlamaIndex workflow.

Next

• Get a key at console.unzoi.com, if you have not.
• The tool reference — what the model is reading when it chooses between the six tools.
• Stories for context windows — the one habit that most changes how well an agent works against this API.
• Limits — an agent that loops can spend a monthly quota faster than you expect.
• LlamaIndex's own MCP documentation — authoritative for anything about the client itself, including config paths, which move.

Endpoint, for copying: https://api.unzoi.com/mcp