Multiple MCP Servers

Connect an Agent to multiple MCP servers with one MCPTools instance per server.

Agno’s MCP integration supports connecting an Agent to multiple MCP servers at once: create one MCPTools instance per server and pass them all to the Agent.

MultiMCPTools was removed in Agno v3.0. Importing it raises an ImportError; use one MCPTools instance per server, as below. Note that env= is per-instance — pass it to the server that needs it.

Prerequisites

Set up your virtual environment

Mac

uv venv --python 3.12
source .venv/bin/activate

Install the Python dependencies and Node.js, then verify the runtimes:

uv pip install -U "agno[mcp]" openai
node --version
npx --version

Export the keys used by the examples you run:

export OPENAI_API_KEY="your_openai_api_key_here"
export GOOGLE_MAPS_API_KEY="your_google_maps_api_key_here"

The @modelcontextprotocol/server-google-maps npm package is deprecated and no longer supported. The snippets below document this legacy server. Use maintained MCP servers for new projects.

Using multiple MCPTools instances

multiple_mcp_servers.py

import asyncio
import os
from datetime import date, timedelta

from agno.agent import Agent
from agno.tools.mcp import MCPTools


async def run_agent(message: str) -> None:
    """Run the Airbnb and Google Maps agent with the given message."""

    env = {
        **os.environ,
        "GOOGLE_MAPS_API_KEY": os.getenv("GOOGLE_MAPS_API_KEY"),
    }

    # Initialize and connect to multiple MCP servers
    airbnb_tools = MCPTools(command="npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt")
    google_maps_tools = MCPTools(command="npx -y @modelcontextprotocol/server-google-maps", env=env)
    await airbnb_tools.connect()
    await google_maps_tools.connect()

    try:
        agent = Agent(
            tools=[airbnb_tools, google_maps_tools],
            markdown=True,
        )

        await agent.aprint_response(message, stream=True)
    finally:
        await airbnb_tools.close()
        await google_maps_tools.close()


# Example usage
if __name__ == "__main__":
    check_in = date.today() + timedelta(days=30)
    check_out = check_in + timedelta(days=3)
    # Pull request example
    asyncio.run(
        run_agent(
            f"What listings are available in Cape Town for 2 people "
            f"from {check_in.isoformat()} to {check_out.isoformat()}?"
        )
    )

Handling Connection Failures

connect() does not raise when a server is unreachable: it logs the error and leaves the instance uninitialized, so the Agent can still run with the servers that did connect. To fail fast when a server is required, check initialized after connecting:

await airbnb_tools.connect()
if not airbnb_tools.initialized:
    raise RuntimeError("Airbnb MCP server is unavailable")

Using async with MCPTools(...) as a context manager instead raises on connection failure.

Avoiding tool name collisions

When using multiple MCP servers, you may encounter tool name collisions. This often happens when the same tool is available in multiple of the servers you are using.

To avoid this, you can use the tool_name_prefix parameter. This will add the given prefix to all tool names coming from the MCPTools instance.

import asyncio

from agno.agent import Agent
from agno.tools.mcp import MCPTools


async def run_agent():
    # Development environment tools
    dev_tools = MCPTools(
        transport="streamable-http",
        url="https://docs.agno.com/mcp",
        # By providing this tool_name_prefix, all the tool names will be prefixed with "dev_"
        tool_name_prefix="dev",
    )
    await dev_tools.connect()

    agent = Agent(tools=[dev_tools])
    await agent.aprint_response("Which tools do you have access to? List them all.")

    await dev_tools.close()


if __name__ == "__main__":
    asyncio.run(run_agent())