Filesystem MCP Integration

Guide for integrating filesystem operations with PraisonAI agents using MCP

MCP(...) accepts three equivalent construction forms — see Three equivalent forms.

Add Filesystem Tool to AI Agent

Diagram

Quick Start

Install Dependencies
Make sure you have Node.js installed, as the MCP server requires it:
bash
```
pip install praisonaiagents mcp
```
Set API Key
Set your OpenAI API key as an environment variable in your terminal:
bash
```
export OPENAI_API_KEY=your_openai_api_key_here
```

Create a file

Create a new file filesystem_agent.py with the following code:

python

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")

Run the Agent
Execute your script:
bash
```
python filesystem_agent.py
```