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

# Sequential Thinking

> Combine the sequential-thinking MCP server with YFinanceTools to reason step by step over stock data.

```python sequential_thinking.py theme={null}
"""
This example demonstrates how to use multiple MCP servers in a single agent.

Prerequisites:
- Google Maps:
    - Set the environment variable `GOOGLE_MAPS_API_KEY` with your Google Maps API key.
    You can obtain the API key from the Google Cloud Console:
    https://console.cloud.google.com/projectselector2/google/maps-apis/credentials

    - You also need to activate the Address Validation API for your .
    https://console.developers.google.com/apis/api/addressvalidation.googleapis.com
"""

import asyncio
from textwrap import dedent

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

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


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

    async with (
        MCPTools(
            command="npx -y @modelcontextprotocol/server-sequential-thinking"
        ) as sequential_thinking_mcp_tools,
    ):
        agent = Agent(
            tools=[
                sequential_thinking_mcp_tools,
                YFinanceTools(),
            ],
            instructions=dedent("""\
                ## Using the think tool
                Before taking any action or responding to the user after receiving tool results, use the think tool as a scratchpad to:
                - List the specific rules that apply to the current request
                - Check if all required information is collected
                - Verify that the planned action complies with all policies
                - Iterate over tool results for correctness

                ## Rules
                - Its expected that you will use the think tool generously to jot down thoughts and ideas.
                - Use tables where possible\
                """),
            markdown=True,
        )

        await agent.aprint_response(message, stream=True)


# Example usage
# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    # Pull request example
    asyncio.run(run_agent("Write a report comparing NVDA to TSLA"))
```

## Run the Example

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

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

  <Step title="Prepare Node.js">
    The MCP server runs with `npx`. Install Node.js, then verify the commands:

    ```bash theme={null}
    node --version
    npx --version
    ```
  </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 `sequential_thinking.py`, then run:

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

Full source: [cookbook/91\_tools/mcp/sequential\_thinking.py](https://github.com/agno-agi/agno/blob/main/cookbook/91_tools/mcp/sequential_thinking.py)