> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-codex-docs-audit-20260719-0149.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP CLI

> Run an interactive CLI chat loop against a GitHub MCP server agent.

Show how to run an interactive CLI to interact with an agent equipped with MCP tools.

<Warning>
  This example starts the retired npm GitHub MCP server. The fence remains byte-matched to v2.7.4. Replace that command in the saved file with [GitHub's maintained MCP server](https://github.com/github/github-mcp-server) before running it.
</Warning>

```python cli.py theme={null}
"""Show how to run an interactive CLI to interact with an agent equipped with MCP tools.

This example uses the MCP GitHub Agent. Example prompts to try:
- "List open issues in the repository"
- "Show me recent pull requests"
- "What are the repository statistics?"
- "Find issues labeled as bugs"
- "Show me contributor activity"

Run: `uv pip install agno mcp openai` to install the dependencies
"""

import asyncio
from textwrap import dedent

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

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


async def run_agent(message: str) -> None:
    """Run an interactive CLI for the GitHub agent with the given message."""

    # Create a client session to connect to the MCP server
    async with MCPTools("npx -y @modelcontextprotocol/server-github") as mcp_tools:
        agent = Agent(
            tools=[mcp_tools],
            instructions=dedent("""\
                You are a GitHub assistant. Help users explore repositories and their activity.

                - Use headings to organize your responses
                - Be concise and focus on relevant information\
            """),
            markdown=True,
        )

        # Run an interactive command-line interface to interact with the agent.
        await agent.acli_app(input=message, stream=True)


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

if __name__ == "__main__":
    # Pull request example
    asyncio.run(
        run_agent(
            "Tell me about Agno. Github repo: https://github.com/agno-agi/agno. You can read the README for more information."
        )
    )
```

## 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 environment variables">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export GITHUB_PERSONAL_ACCESS_TOKEN="your_github_personal_access_token_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:GITHUB_PERSONAL_ACCESS_TOKEN="your_github_personal_access_token_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Use GitHub's maintained MCP server">
    Install and start Docker. Then replace `npx -y @modelcontextprotocol/server-github` in the saved file with `docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN -e GITHUB_READ_ONLY=1 ghcr.io/github/github-mcp-server`.

    ```bash theme={null}
    docker --version
    ```
  </Step>

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

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

Full source: [cookbook/91\_tools/mcp/cli.py](https://github.com/agno-agi/agno/blob/v2.7.4/cookbook/91_tools/mcp/cli.py)