-
securityA
license-
qualityA Model Context Protocol server that integrates with Notion's API to manage personal todo lists, allowing users to view, add, and update tasks directly from Claude.
Last updated -
27
MIT License
Manages environment variables for the application, including the OpenAI API key and MCP server URL configuration.
Provides the server framework for the MCP implementation, exposing endpoints for tool discovery and JSON-RPC calls to interact with the to-do list application.
Provides version control for the MCP implementation, with instructions for cloning the repository during installation.
Hosts the source code repository for the to-do list MCP implementation, making it accessible for users to download and install.
Enables the CLI client to interact with OpenAI's LLMs to interpret natural language commands and execute appropriate function calls for managing tasks.
Serves as the programming language for both the server and client implementations, with support for Python 3.10+ required.
TODO MCP CLI & Server
This repository contains a minimal Model Context Protocol (MCP) implementation for a to-do list application, including:
FastAPI server (
server/): exposes a/toolsendpoint for tool discovery and an/rpcendpoint for JSON-RPC calls to perform operations on tasks.CLI client (
client/cli.py): a Python command-line interface that interacts with an LLM (via OpenAI) and the MCP server to create, list, and complete tasks using function calls.
Features
Add tasks with title, content, and optional due date
List all tasks
Mark tasks as completed
Server-side task ID generation
JSON-RPC 2.0 compliance for tool invocation
Prerequisites
Python 3.10+
pipenv or
venvfor virtual environmentsAn OpenAI API key
Installation
Clone the repo:
git clone https://github.com/oseni99/todo-mcp cd todo-mcpCreate and activate a virtual environment:
python3 -m venv .venv source .venv/bin/activateInstall dependencies:
pip install -r requirements.txtCreate a
.envin the project root:OPENAI_API_KEY=sk-... MCP_SERVER=http://127.0.0.1:8000
Directory Structure
todoMCP/
├── client/ # CLI client code
│ └── cli.py # Main entrypoint for the MCP-CLI
├── server/ # FastAPI server code
│ ├── handlers.py # Business logic for add, list, complete
│ ├── tools.py # JSON-Schema tool manifest
│ └── main.py # FastAPI app with /tools and /rpc
├── .env # Environment variables (not committed)
├── requirements.txt # Python dependencies
└── README.md # This file
Running the Server
fastapi dev server/main.py
Visit http://127.0.0.1:8000/docs for interactive API docs.
Running the CLI
From the project root:
python -m client.cli
Type natural language commands at the prompt, for example:
> Create a task titled "Write blog post" with content "Outline first draft" due 2025-05-20
> List my tasks
> Mark the first task as done
> Thanks!
> exit
The CLI will print tool invocations and LLM responses.
This server cannot be installed
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityA Model Context Protocol (MCP) server that provides tools for managing todo items, including creation, updating, completion, deletion, searching, and summarizing tasks.Last updated -37MIT License
- -securityAlicense-qualityA Model Context Protocol server providing comprehensive task management capabilities with support for project organization, task tracking, and automatic PRD parsing into actionable items.Last updated -30MIT License
- Asecurity-licenseAqualityA task management Model Context Protocol server that helps break down user requests into manageable tasks with subtasks, dependencies, and notes, while enforcing a structured workflow with user approval steps.Last updated -176210MIT License