> ## 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.

# MCP Tools

> Connect MCPTools to the filesystem MCP server over a stdio session and summarize a file.

```python mcp_tools.py theme={null}
"""
Mcp Tools
=============================

Demonstrates mcp tools.
"""

import asyncio
import sys
from pathlib import Path

from agno.agent import Agent
from agno.tools.mcp import MCPTools
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

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


async def main(prompt: str) -> None:
    # Initialize the MCP server
    server_params = StdioServerParameters(
        command="npx",
        args=[
            "-y",
            "@modelcontextprotocol/server-filesystem",
            str(Path(__file__).parent.parent),
        ],
    )
    # Create a client session to connect to the MCP server
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            # Initialize the MCP toolkit
            mcp_tools = MCPTools(session=session)
            await mcp_tools.initialize()

            # Create an agent with the MCP toolkit
            agent = Agent(tools=[mcp_tools])

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


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

if __name__ == "__main__":
    prompt = (
        sys.argv[1] if len(sys.argv) > 1 else "Read and summarize the file ./LICENSE"
    )
    asyncio.run(main(prompt))
```

## 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. Run the example**

Run the example from the repository root:

```bash theme={null}
python cookbook/91_tools/mcp_tools.py
```

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


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