Overview
What is My_tasks_mcp?
My_tasks_mcp is a simple MCP server for task management that uses a Google Sheet as its database. It is intended for users who want to manage tasks through a chat interface (e.g., Claude Desktop) while storing data in a familiar spreadsheet format.
How to use My_tasks_mcp?
Clone the repository, create and activate a Python virtual environment, then set up a Google service account with Drive and Sheets APIs enabled. Download the service account JSON file as googleserviceaccount.json and place it in the project root. Create a Google Sheet named “MyTasks” and share it with the service account email. Install dependencies with uv add google-auth google-auth-oauthlib gspread mcp oauth2client. Finally, add the MCP server configuration to your Claude Desktop app using the command uv with the arguments shown in the README, pointing to the project’s main.py.
Key features of My_tasks_mcp
- Uses a Google Sheet as the backend database.
- Provides task management capabilities via the MCP protocol.
- Simple setup with a service account for authentication.
- Designed to work with Claude Desktop or other MCP hosts.
Use cases of My_tasks_mcp
- Managing personal to‑do lists through a conversational AI interface.
- Storing and updating tasks in a shareable Google Sheet.
- Demonstrating how to build an MCP server with a cloud‑based data source.
FAQ from My_tasks_mcp
What dependencies are required?
Install google-auth, google-auth-oauthlib, gspread, mcp, and oauth2client using uv add in your virtual environment.
How do I set up the Google Sheet?
Create a new Google Sheet named exactly “MyTasks”, then share it (with edit permissions) with the email address of your Google service account.
What is the MCP configuration for Claude Desktop?
Add a JSON entry under mcpServers with the command uv and arguments ["--directory", "/path/to/your/project/mcp_server/", "run", "main.py"].
How do I authenticate with Google?
Download a service account JSON key file from the Google Cloud Console, rename it to googleserviceaccount.json, and place it in the root folder of the project.
What runtime environment is needed?
Python 3 with a virtual environment. Create it with python3 -m venv venv and activate it (source venv/bin/activate on macOS, venv\Scripts\activate on Windows).
