Stdio Transport

Transports in the Model Context Protocol (MCP) define how messages are sent and received. The Agno integration supports the three existing types: stdio, SSE and Streamable HTTP. The stdio (standard input/output) transport is the default one in Agno’s integration. It works best for local integrations. To use it, simply initialize the MCPTools class with its command argument. The command you want to pass is the one used to run the MCP server the agent will have access to. For example uvx mcp-server-git, which runs a git MCP server:

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.mcp import MCPTools

async def run_mcp_agent():
    # Initialize the MCP tools
    mcp_tools = MCPTools(command=f"uvx mcp-server-git")

    # Connect to the MCP server
    await mcp_tools.connect()

    # Initialize the Agent
    agent = Agent(model=OpenAIChat(id="gpt-4o"), tools=[mcp_tools])

    # Run the agent
    await agent.aprint_response("What is the license for this project?", stream=True)

    # Close the MCP connection
    await mcp_tools.close()

You can also use multiple MCP servers at once, with the MultiMCPTools class. For example:

import asyncio
import os

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


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 the MultiMCPTools instance
    multi_mcp_tools = MultiMCPTools(
        [
            "npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt",
            "npx -y @modelcontextprotocol/server-google-maps",
        ],
        env=env,
    )

    # Connect to the MCP servers
    await multi_mcp_tools.connect()

    # Initialize the Agent
    agent = Agent(
        tools=[mcp_tools],
        markdown=True,
        show_tool_calls=True,
    )

    # Run the agent
    await agent.aprint_response(message, stream=True)

    # Close the MCP connections
    await multi_mcp_tools.close()


# Example usage
if __name__ == "__main__":
    # Pull request example
    asyncio.run(
        run_agent(
            "What listings are available in Cape Town for 2 people for 3 nights from 1 to 4 August 2025?"
        )
    )

Introduction

Concepts

Other

How to

Stdio Transport