Skip to main content

A personal assistant AI agent built with the Model Context Protocol (MCP)

Project description

MCP Personal Assistant Agent

A versatile personal assistant AI agent built with the Model Context Protocol (MCP) that helps with calendar, tasks, emails, and more.

Overview

This project is a Model Context Protocol (MCP) server that provides a set of tools for a personal assistant agent. It can be integrated with MCP clients like Claude for Desktop to give AI assistants the ability to:

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

Requirements

⚠️ IMPORTANT: Python 3.10 or higher is required for the MCP SDK. The server will not work with earlier Python versions.

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

Installation

  1. Clone the repository:
git clone https://github.com/yourusername/mcp-pa-ai-agent.git
cd mcp-pa-ai-agent
  1. Ensure you have Python 3.10+:
python --version
  1. If your system Python is older 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
  1. Install dependencies:
pip install -r requirements.txt
  1. Configure environment variables by copying the example file:
cp .env.example .env
  1. Edit the .env file with your API credentials and settings.

Running the Server

Start the MCP server with:

python mcp_server.py

The server will start and listen 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 at:

    • 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're using a virtual environment, make sure to point to the Python executable in that environment.

  1. Restart Claude for Desktop

Available Tools

Calendar

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

Tasks

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

Email

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

Knowledge

  • web_search: Search the web for information
  • get_weather: Get current weather information
  • get_news: Retrieve 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 about a device's current state

Configuration

The server requires various API keys and credentials to access different services:

  • Google API: For calendar and email functionality (OAuth2 credentials)
  • Weather API: For weather information
  • News API: For news retrieval
  • Home Assistant: For smart home control

Refer to the .env.example file for all configurable options.

Troubleshooting

Python Version Issues

If you see an error like:

Error: Python 3.10 or higher is required for the MCP server.

You need to upgrade your Python version or use a virtual environment with Python 3.10+.

MCP SDK Installation Issues

If you encounter problems installing the MCP SDK:

ERROR: Could not find a version that satisfies the requirement mcp>=1.2.0

Make sure you're using Python 3.10+ and pip is updated:

pip install --upgrade pip

Development

To add new functionality to the server, you can:

  1. Create a new module in the modules/ directory
  2. Implement functions with the @mcp.tool() decorator
  3. Import your module in mcp_server.py

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iflow_mcp_mcp_pa_ai_agent-0.1.0.tar.gz (86.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

iflow_mcp_mcp_pa_ai_agent-0.1.0-py3-none-any.whl (20.2 kB view details)

Uploaded Python 3

File details

Details for the file iflow_mcp_mcp_pa_ai_agent-0.1.0.tar.gz.

File metadata

File hashes

Hashes for iflow_mcp_mcp_pa_ai_agent-0.1.0.tar.gz
Algorithm Hash digest
SHA256 0a8161860b1e160c4607d72a41397b9820ef0ee23e230a51510fba824f5efc01
MD5 1e84ac8767023aaea1717b5f317c7ddb
BLAKE2b-256 adfb029e506c843c5798976cc5d4e1e01df4266e89c1fb9e1a7461313005b8be

See more details on using hashes here.

File details

Details for the file iflow_mcp_mcp_pa_ai_agent-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for iflow_mcp_mcp_pa_ai_agent-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d5484c43c99c5189f75708ca9f2b4d054acb086cc0572fcabac8216d47a4fc07
MD5 23b889d96164cb5a6f87b7f58c69aaba
BLAKE2b-256 49395bcf5ed615f34572dfac720f8f46cf7b6ea0b2e2ab85ffd8b774537af81d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page