Todo MCP Server

@stilllovee

Basic information

About Todo MCP Server

MCP server allows agents to break tasks down and execute them sequentially.

Todo MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "todo": {
      "command": "npx",
      "args": [
        "github:stilllovee/todo-mcp-server"
      ]
    }
  }
}

Todo MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Todo?

Todo is a Model Context Protocol (MCP) server providing an autonomous task management system with SQLite persistence, supporting both stdio and HTTP (Streamable) transports for AI agents.

How to use Todo?

Install via npm install or use Docker. For stdio transport, configure in Claude Desktop or GitHub Copilot using npx github:stilllovee/todo-mcp-server or pointing to a local clone. For HTTP transport, start with npm run start:http (port 8123) and connect at http://localhost:8123/mcp.

Key features of Todo

Generates random 6‑character alphanumeric strings
Autonomous task management with add and next tools
Supports both stdio and HTTP (SSE) transports
Session isolation – each session has an independent task list
Persistent SQLite storage (local or Docker volume)
Fully compliant with MCP specifications

Use cases of Todo

AI agent autonomously creating and managing task lists from high‑level requests
Step‑by‑step task execution workflow using the next tool
Multi‑session task management (e.g., separate lists per user or conversation)

Frequently asked questions

What transports does Todo support?

Todo supports stdio (stdin/stdout) for standard MCP communication and HTTP with Server‑Sent Events for real‑time notifications.

How do I deploy Todo with Docker?

Use `docker-compose up -d` for quick start, or manually build the image with `docker build -t todo-mcp-server .` and run with `docker run -d -p 8123:8123 -v todo-mcp-data:/app/data --restart unless-stopped todo-mcp-server`.

How is data persisted?

Tasks are stored in an SQLite database. When using Docker, data is kept in a named volume; locally the database file is created in the app’s data directory.

Does Todo support session‑based task management?

Yes. Each session (identified by a `session_id`) maintains its own separate task list, and the HTTP transport manages sessions with an `mcp-session-id` header.

What dependencies are required?

Node.js and npm for local development; Docker (and optionally Docker Compose) for containerized deployment.

Comments

More Productivity MCP servers

Local MCP (LMCP)

lanchuske

Local tools that let your AI use Mail, Calendar, Contacts, Teams, Slack, WhatsApp, OneDrive, Google Drive, Notion, Outlook and Office files on Mac and Windows. Runs on your computer.

OmniSocials

Official OmniSocials MCP server — schedule and publish posts, stories, and reels across 11 platforms (Instagram, Facebook, LinkedIn, YouTube, TikTok, X, Pinterest, Bluesky, Threads, Mastodon, Google Business), plus media

LeaseCommand

Copliancy Inc

Lease and contract records with ASC 842 lease accounting data: sites, leases, rent schedules, critical dates and journal entries, with confirmed write operations.

Snipzr

Snipzr (snipzr.com) is a URL shortener. Its remote MCP server lets your AI assistant create and batch-create short links on your own domain, update and list them, read cookie-less click stats with bots shown separately,

BoardMark

I C Develop Co., Ltd

Plan and track your team's work in BoardMark from any AI agent: find, create and move issues, run Scrum sprints, comment and keep project docs current. OAuth sign-in, your own permissions.