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

# Filesystem MCP Integration

> Guide for integrating filesystem operations with PraisonAI agents using MCP

## Add Filesystem Tool to AI Agent

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
flowchart LR
    In[Query] --> Agent[AI Agent]
    Agent --> Tool[Filesystem MCP]
    Tool --> Agent
    Agent --> Out[Answer]
    
    style In fill:#8B0000,color:#fff
    style Agent fill:#2E8B57,color:#fff
    style Tool fill:#FFA500,color:#fff
    style Out fill:#8B0000,color:#fff
```

## Quick Start

<Steps>
  <Step title="Install Dependencies">
    Make sure you have Node.js installed, as the MCP server requires it:

    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    pip install praisonaiagents mcp
    ```
  </Step>

  <Step title="Set API Key">
    Set your OpenAI API key as an environment variable in your terminal:

    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    export OPENAI_API_KEY=your_openai_api_key_here
    ```
  </Step>

  <Step title="Create a file">
    Create a new file `filesystem_agent.py` with the following code:

    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    from praisonaiagents import Agent, MCP
    import os

    # Define allowed directories for filesystem access
    allowed_dirs = [
        "/Users/username/Desktop",
        "/path/to/other/allowed/dir"
    ]

    # Use a single string command with allowed directories
    filesystem_agent = Agent(
        instructions="""You are a helpful assistant that can interact with the filesystem.
        Use the available tools when relevant to manage files and directories.""",
        llm="gpt-4o-mini",
        tools=MCP("npx -y @modelcontextprotocol/server-filesystem", args=allowed_dirs)
    )

    filesystem_agent.start("List files in the allowed directories")
    ```
  </Step>

  <Step title="Run the Agent">
    Execute your script:

    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    python filesystem_agent.py
    ```
  </Step>
</Steps>

<Note>
  **Requirements**

  * Python 3.10 or higher
  * Node.js installed on your system
  * OpenAI API key (for the agent's LLM)
  * Read/write access to the specified directories
</Note>