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

# Test Client

> MCP client example: an agent that operates an AgentOS through its MCP server.

````python test_client.py theme={null}
"""
MCP client example: an agent that operates an AgentOS through its MCP server.

First run the AgentOS with the MCP server enabled:

```bash
.venvs/demo/bin/python cookbook/05_agent_os/mcp_demo/mcp_server_example.py
```

Then run this client in a second terminal. It connects to the AgentOS MCP server
at /mcp and drives it through the 8 built-in tools: discover the OS
(get_agentos_config), run components (run_agent / run_team / run_workflow),
resolve pauses (continue_run), stop runs (cancel_run), and browse conversations
(get_sessions / get_session_runs).
"""

import asyncio
from uuid import uuid4

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

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

# This is the URL of the MCP server we want to use.
server_url = "http://localhost:7777/mcp"

session_id = f"session_{uuid4()}"


async def run_agent() -> None:
    async with MCPTools(
        transport="streamable-http", url=server_url, timeout_seconds=60
    ) as mcp_tools:
        agent = Agent(
            model=OpenAIResponses(id="gpt-5.5"),
            tools=[mcp_tools],
            instructions=[
                "You operate an AgentOS through its MCP tools.",
                "Call get_agentos_config first to discover the agents, teams, and workflows you can run.",
                "Use the run tools to delegate work, and the session tools to review past conversations.",
            ],
            user_id="john@example.com",
            session_id=session_id,
            db=InMemoryDb(),
            add_session_state_to_context=True,
            add_history_to_context=True,
            markdown=True,
        )

        await agent.aprint_response(
            input="Which agents do I have in my AgentOS?", stream=True, markdown=True
        )

        # await agent.aprint_response(
        #     input="Use my web research agent to find the latest news about AI",
        #     stream=True,
        #     markdown=True,
        # )

        ## Session history
        # await agent.aprint_response(
        #     input="List my recent sessions and summarize what the last conversation was about.",
        #     stream=True,
        #     markdown=True,
        # )


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

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

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[mcp]" openai
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```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"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `test_client.py`, then run:

    ```bash theme={null}
    python test_client.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/mcp\_demo/test\_client.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/mcp_demo/test_client.py)