MCP Pa Ai Agent

🚀 MCP Personal Assistant Agent

A powerful personal assistant AI agent built using the Model Context Protocol (MCP) to help manage calendars, tasks, emails, etc.

🚀 Quick Start

The MCP Personal Assistant Agent is a server based on the MCP protocol. It offers a set of tools to build a personal assistant agent. It can integrate with MCP clients like Claude for Desktop, empowering AI assistants with the following capabilities:

• Manage calendar events
• Track tasks and to - dos
• Read and send emails
• Search the web and retrieve information
• Control smart home devices

✨ Features

This project provides a comprehensive set of features through various tools:

Calendar

• get_events: Retrieve upcoming calendar events
• create_event: Schedule new calendar events

Tasks

• list_tasks: View all tasks or filter by status
• add_task: Create new tasks
• update_task_status: Mark tasks as pending, in - progress, or completed

Email

• get_emails: List recent emails in the inbox
• read_email: View the full - text content of a specific email
• send_email: Compose and send new emails

Knowledge Base

• web_search: Search for information on the web
• get_weather: Get current weather information
• get_news: Retrieve the latest news articles

Smart Home

• list_devices: View all smart home devices
• control_device: Control smart home devices (lights, thermostats, etc.)
• get_device_state: Get detailed information on the current state of a device

📦 Installation

Prerequisites

⚠️ Important Note

The MCP SDK requires Python 3.10 or higher. Older versions of Python will not work.

• Python 3.10+
• MCP SDK 1.2.0+
• Necessary Python packages (see requirements.txt)

Installation Steps

1. Clone the repository:

git clone https://github.com/yourusername/mcp-pa-ai-agent.git
cd mcp-pa-ai-agent

2. Ensure you are using Python 3.10+:

python --version

3. If the system Python version is lower than 3.10, set up a compatible environment:

# Using conda
conda create -n mcp-env python=3.10
conda activate mcp-env

# Or using venv (if Python 3.10+ is installed elsewhere)
python3.10 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

4. Install dependencies:

pip install -r requirements.txt

5. Copy the example environment variable file:

cp .env.example .env

6. Edit the .env file as needed to configure API credentials and settings.

💻 Usage Examples

Running the Server

python mcp_server.py

The server starts and listens for MCP client connections.

Connecting to Claude for Desktop

1. Install Claude for Desktop

2. Configure Claude for Desktop to use this MCP server by editing the configuration file:

   • MacOS/Linux: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json

3. Add the following configuration:

{
  "mcpServers": {
    "personal-assistant": {
      "command": "/path/to/python",
      "args": [
        "/absolute/path/to/mcp-pa-ai-agent/mcp_server.py"
      ]
    }
  }
}

If you are using a virtual environment, make sure to point to the Python executable in that environment.

4. Restart Claude for Desktop