About Todo MCP Server
Todo MCP Server is a minimal Todo application built for demonstrating and testing MCP interactions. It supports basic item management and structured task creation with priority and due-date fields.
Key features
- 01List and view todo items
- 02Add and remove items
- 03Clear the todo list
- 04Create tasks with priority and due date
Use cases
- 01Track a basic list of tasks
- 02Review a specific todo item
- 03Create a task with priority and deadline
- 04Test MCP resources, tools, and prompts
MCP support
The server exposes todo-list and item-view resources, tools for adding, removing, and clearing items, and a prompt for structured task creation.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMETodo MCP Server
A simple Todo application built using MCP (Model Context Protocol) Server for testing and demonstrating MCP interactions.
Overview
This repository contains a minimal Todo application implemented as an MCP server. It allows you to:
- List all todo items
- View specific todo items
- Add new todo items
- Remove todo items
- Clear all todo items
- Create structured todo tasks with metadata
This project serves as a test bed for interacting with Model Context Protocol servers and understanding how to build and expose functionality through the MCP protocol. For more information about the Model Context Protocol, visit modelcontextprotocol.io.
Requirements
- Python 3.10+
- uv (Python package installer)
Installation
- Clone the repository:
git clone https://github.com/idsulik/todo-mcp-server.git
cd todo-mcp-server
- Install dependencies using uv:
uv pip install -e .
Adding to MCP Servers List
To add this server to your MCP servers list, use the following command:
mcp install server.py --name "Todo MCP"
This registers the server with the Claude Desktop app or other MCP-enabled applications.
Alternatively, if you want to test the server with the MCP Inspector, you can use:
mcp dev server.py
This will launch the server along with the MCP Inspector interface for easy testing and debugging.
API Usage
The server exposes the following MCP resources and tools:
Resources
- List all todo items:
GET todo://list
- View a specific todo item:
GET todo://view/{item_idx}
Where item_idx is the index of the item you want to view.
Prompts
- Create a structured todo task:
create_task(task_name: str, priority: str = "medium", due_date: str = "")
This prompt helps format todo tasks with priority levels and due dates. Parameters:
task_name: The name/description of the taskpriority: Task priority (low, medium, high)due_date: When the task is due (optional)
Tools
- Add a new todo item:
add_todo(value: str)
- Remove a todo item:
remove_todo(item_idx: int)
- Clear all todo items:
clear_todo()
Adding to MCP Configuration Manually
If you prefer to add the server manually to your MCP configuration, you can add the following JSON to your Claude
Desktop configuration file (typically located at ~/.claude-desktop/claude_desktop_config.json on Mac/Linux or
C:\Users\YourUsername\AppData\Roaming\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"todo": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"/path/to/your/server.py"
]
}
}
}
Replace /path/to/your/server.py with the absolute path to your server.py file. Make sure to use absolute paths, not
relative paths.
Using Docker
You can also run this MCP server using Docker without installing anything locally. Add the following to your Claude Desktop configuration:
{
"mcpServers": {
"todo": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"idsulik/todo-mcp-server"
]
}
}
}
The Docker image will automatically pull from Docker Hub if it's not already on your system.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.