> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Client

> Connect an OpenAI agent to one SSE MCP server, then combine separate SSE and stdio MCPTools instances.

Connect to one or more MCP servers with separate MCPTools instances, including a deprecated standalone SSE transport.

```python client.py theme={null}
"""
Show how to connect to MCP servers that use the SSE transport using our MCPTools class.
Check the README.md file for instructions on how to run these examples.

Note: SSE as a standalone transport is deprecated. Prefer Streamable HTTP for new servers.
"""

import asyncio

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

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


# This is the URL of the MCP server we want to use.
server_url = "http://localhost:8000/sse"


async def run_agent(message: str) -> None:
    mcp_tools = MCPTools(
        transport="sse",
        url=server_url,
        refresh_connection=True,  # (Optional) Refresh the MCP connection and tools on each run
    )
    await mcp_tools.connect()
    agent = Agent(
        model=OpenAIResponses(id="gpt-5.5"),
        tools=[mcp_tools],
        markdown=True,
    )
    await agent.aprint_response(input=message, stream=True, markdown=True)
    await mcp_tools.close()


# We can connect to multiple MCP servers at once, even if they use different transports.
# In this example we connect to both our example server (SSE transport), and a different server (stdio transport).
async def run_agent_with_multiple_servers(message: str) -> None:
    airbnb_tools = MCPTools(
        command="npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt"
    )
    sse_tools = MCPTools(
        transport="sse",
        url=server_url,
        refresh_connection=True,  # (Optional) Refresh the MCP connection and tools on each run
    )
    await airbnb_tools.connect()
    await sse_tools.connect()
    agent = Agent(
        model=OpenAIResponses(id="gpt-5.5"),
        tools=[airbnb_tools, sse_tools],
        markdown=True,
    )
    await agent.aprint_response(input=message, stream=True, markdown=True)
    await airbnb_tools.close()
    await sse_tools.close()


# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    asyncio.run(run_agent("Do I have any birthdays this week?"))
    asyncio.run(run_agent("What else is on my calendar this week?"))
    asyncio.run(
        run_agent_with_multiple_servers(
            "Can you check when is my mom's birthday, and if there are any AirBnb listings in SF for two people for that day?"
        )
    )
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U "agno[mcp]" openai
```

**2. Prepare Node.js**

The MCP server runs with `npx`. Install Node.js, then verify the commands:

```bash theme={null}
node --version
npx --version
```

**3. Export your OpenAI API key**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**4. Clone Agno**

Clone the pinned Agno source and run the remaining commands from its root:

```bash theme={null}
git clone https://github.com/agno-agi/agno.git
cd agno
git checkout v3.0.4
```

**5. Start the SSE server**

In another terminal, start the companion MCP server on port 8000:

```bash theme={null}
python cookbook/91_tools/mcp/sse_transport/server.py
```

**6. Run the example**

Run the example from the repository root:

```bash theme={null}
python cookbook/91_tools/mcp/sse_transport/client.py
```

Full source: [cookbook/91\_tools/mcp/sse\_transport/client.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/91_tools/mcp/sse_transport/client.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.