MCP TODO Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP TODO Serveradd 'prepare quarterly report' to my tasks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP TODO Server
PortuguΓͺs | English
A robust Model Context Protocol (MCP) server built with NestJS, designed to manage TODO tasks and integrate seamlessly with AI agents like Claude Desktop, ChatGPT, and automation tools like n8n.
π Features
β TODO Management: Full CRUD operations for tasks.
π€ MCP Integration: Exposes TODO operations as MCP tools using both SSE (Server-Sent Events) and Stdio (via CLI integration).
π Swagger UI: Interactive API documentation at
/api/docs.π MCP Inspector: Built-in support for debugging tools with the
@modelcontextprotocol/inspector.π οΈ Modern Tooling: Built with TypeScript, Biome for linting/formatting, and Jest for E2E testing.
Related MCP server: n8n Autopilot MCP SaaS
π οΈ Tech Stack
Framework: NestJS
Protocol: Model Context Protocol (MCP)
Documentation: Swagger/OpenAPI
Linting/Formatting: Biome
π Prerequisites
βοΈ Project Setup
# Install dependencies
$ npm install
# Create environment file
$ cp .env.example .env # Ensure SERVER_PORT=3000 is setπ Compilation and Running
# Development (watch mode)
$ npm run start:dev
# Production mode
$ npm run build
$ npm run start:prodπ API Documentation
Once the server is running, you can access the interactive Swagger documentation at:
http://localhost:3000/api/docs
π€ Using with MCP Clients
1. ChatGPT Desktop (macOS)
Go to Settings > Advanced and enable Developer Mode.
Go to Settings > Connectors and click Create.
Set URL to
http://localhost:3000/sseand Authentication to None.
2. MCP Inspector (Debugging)
To debug the MCP tools locally:
$ npm run inspectorThis will open the MCP Inspector at http://localhost:3000/sse.
3. Claude Desktop
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"mcp-todo": {
"command": "node",
"args": ["/path/to/project/dist/main.js"]
}
}
}π§ͺ Testing
# Unit tests
$ npm run test
# End-to-end tests
$ npm run test:e2eπ License
This project is UNLICENSED.
This server cannot be deployed
Maintenance
Related MCP Connectors
ADHD-friendly tasks, notes & projects for LucidNest - 18 tools, scoped tokens, Streamable HTTP.
AI-native task management: list, create, update and archive tasks with rich context for AI agents
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
- mcpOAuthnet.todoist
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
Related MCP Servers
- AlicenseAqualityDmaintenanceA TypeScript-based MCP server that enables users to manage tasks through natural conversation with Claude. Features complete CRUD operations, priority management, tagging, search functionality, and intelligent productivity insights with robust Zod validation.646MIT
- FlicenseNot gradedqualityDmaintenanceAn AI-powered workflow automation platform that builds and executes n8n workflows based on natural language descriptions. It integrates a NestJS-based MCP server to facilitate seamless task automation and management.-
- AlicenseNot gradedqualityDmaintenanceA TypeScript-based server that enables AI agents to create, prioritize, and manage ordered task lists for complex projects. It provides tools for task tracking, status filtering, and progress statistics with persistent storage.7 npm1ISC
- AlicenseNot gradedqualityDmaintenanceA NestJS-based server that enables AI agents to interact with Logseq graphs through its HTTP API for managing notes, journals, and blocks. It features specialized tools for project development tracking, including progress logs, technical decisions, and workflow prompts.23 npmMIT