Vitsaus/mcp-todo-list
If you are the rightful owner of mcp-todo-list and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Model Context Protocol (MCP) server is a framework designed to facilitate communication between AI models and client applications, enabling efficient task management and AI querying.
MCP Todo
My first attempt to understand and learn how MCP servers/AI querying works. This is not suitable for production, this is very naive implementation which can quickly use your tokens with large amount of tasks.
This workspace contains a simple mcp todo app with:
- backend: NestJS server with in-memory tasks and an MCP controller that forwards prompts to OpenAI and creates tasks
- frontend: Vite + React UI
To run:
-
Install dependencies for backend and frontend cd backend && npm install cd ../frontend && npm install
-
Set OPENAI_API_KEY in backend/.env
-
Start backend: cd backend && npm run start:dev
-
Start frontend: cd frontend && npm run dev
The MCP endpoint is POST /mcp/create and expects { prompt } in the body.
Usage:
In localhost:3000 you can control tasks with chat prompts.
- Create task hello world
- List tasks 1,2
- Set task 1 as done
In Visual Studio Code chat/ai window you can call:
- #mcp list tasks
- #mcp create task hello world
- #mcp set task 1 as done
and so on...