Skip to main content
Glama
laibaafreen

Task / To-Do Manager

by laibaafreen

Task / To-Do Manager — MCP Server

A small MCP server that lets an AI assistant manage a simple to-do list. Tasks are stored in tasks.json in this folder — no database required.

Setup

python -m venv venv
source venv/bin/activate      # Windows: venv\Scripts\activate
pip install -r requirements.txt

Running the server

python server.py

The server talks over stdio (standard input/output), so it's meant to be launched by an MCP client (like MCP Inspector, or an AI assistant configured to use it) — not run and watched directly in a plain terminal.

To test it by hand, run:

mcp dev server.py

and open the URL Inspector prints. From there you can click each tool below and try it yourself.

Tools

Tool

What it does

Example call

add_task(title)

Adds a new task

add_task("Buy groceries"){"id": 1, "title": "Buy groceries", "done": false}

list_tasks()

Lists every task

list_tasks()[{"id": 1, "title": "Buy groceries", "done": false}]

get_task(task_id)

Gets one task by id

get_task(1){"id": 1, "title": "Buy groceries", "done": false}

complete_task(task_id)

Marks a task done

complete_task(1){"id": 1, "title": "Buy groceries", "done": true}

delete_task(task_id)

Deletes a task

delete_task(1){"deleted": 1}

Bonus resource

tasks://pending — a read-only JSON list of every task that isn't done yet. Unlike a tool, it never changes any data; it only displays it.

Error handling

Every tool checks its input first. Missing or invalid data (an empty title, or an id that doesn't exist) returns a clear {"error": "..."} message instead of crashing the server.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/laibaafreen/mcp-todo-manager'

If you have feedback or need assistance with the MCP directory API, please join our Discord server