mcp-todo-server
Click on "Install 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-serverShow me the daily summary of 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
Basic MCP (Model Context Protocol) server that exposes a to-do list,
implemented in TypeScript with the official @modelcontextprotocol/sdk.
Extra Class Assignment 1 — Programming IV — Model Context Protocol.
Exposed capabilities
Type | Name | Description |
Resource |
| Returns the complete list of tasks stored in |
Tool |
| Adds a new task (name, description, priority) |
Tool |
| Marks an existing task as completed, given its ID |
Prompt |
| Generates a summary template of the current state of the tasks |
Related MCP server: MCP Todo Server
Project structure
mcp-todo-server/
├── src/
│ └── server.ts # Servidor MCP principal
├── tasks.json # Almacenamiento de tareas (base de datos simple)
├── tsconfig.json # Configuración de TypeScript
├── package.json
└── README.mdRequirements
Node.js 18 or higher
npm
Installation
npm installThis installs the dependencies: @modelcontextprotocol/sdk, zod (schema validation),
and as development dependencies typescript, @types/node, and tsx.
Execution
Development mode (runs the TypeScript directly, without compiling):
npm run devProduction mode (compiles to JavaScript and then runs):
npm run build
npm startThe server communicates via stdio (standard input/output), which is the transport used by Claude Desktop and most local MCP clients. When it starts correctly you will see in the terminal:
Servidor MCP 'mcp-todo-server' corriendo por stdio...That message goes out through stderr on purpose, so as not to interfere with the JSON-RPC messages
that go through stdout.
How to test it without a graphical client
You can use the official MCP Inspector, which opens a web interface to invoke
Resources, Tools, and Prompts by hand:
npx @modelcontextprotocol/inspector npx tsx src/server.tsExample usage of each capability
Read the tasks resource → returns the tasks array from tasks.json in JSON format.
Tool add_task, arguments:
{ "name": "Repasar JSON-RPC", "description": "Leer la especificación 2.0", "priority": "media" }Tool complete_task, arguments:
{ "id": 1 }Prompt daily_summary takes no arguments: it automatically builds a summary with
the pending and completed tasks, grouped by priority.
Author
Camila — National University of Costa Rica, Programming IV.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceThis MCP server provides tools to manage a todo list with CRUD operations, enabling listing, creating, updating, and deleting todos.
- AlicenseNot gradedqualityCmaintenanceA CRUD todo list server that exposes tools to create, list, and conclude tasks, compatible with any MCP host.8MIT
- AlicenseBqualityNot gradedmaintenanceA basic MCP server for managing a todo list stored in a local JSON file, enabling task creation, completion, listing, and daily summary generation.28MIT
Related MCP Connectors
A basic MCP server to operate on the Postman API.
MCP server for generating rough-draft project plans from natural-language prompts.
A MCP server built for developers enabling Git based project management with project and personal…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/cchanquispe08-blip/mcp-todo-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server