MCP Task Manager Server

What is MCP Task Manager Server?

A local Model Context Protocol (MCP) server providing backend tools for client-driven project and task management using a SQLite database. It is designed for MCP clients such as AI agents or scripts that need to manage structured task data within distinct projects.

How to use MCP Task Manager Server?

Install dependencies with npm install, then run in development mode with npm run dev (uses stdio transport). For production, build with npm run build and start with npm start. The database path and log level can be configured via the DATABASE_PATH and LOG_LEVEL environment variables, respectively.

Key features of MCP Task Manager Server

• Project-based organization of tasks.
• SQLite persistence with a local database file.
• Client-driven workflow; server provides tools, not strategies.
• Full MCP compliance for tool definition and communication.
• Supports task creation, status updates, subtasks, and next-task identification.
• Import/export project data in JSON format.

Use cases of MCP Task Manager Server

• AI agents managing a personal to-do list across multiple projects.
• Scripts automating project task tracking without external services.
• Local development integration for prototyping task management workflows.
• Headless task management backend for chat or terminal-based interfaces.

FAQ from MCP Task Manager Server

Where is the database stored?

By default, the SQLite database is stored in ./data/taskmanager.db. You can override this path with the DATABASE_PATH environment variable.

How do I configure the log level?

Set the LOG_LEVEL environment variable to debug, info, warn, or error. The default is info.

What transport does the server use?

The server communicates via stdio (standard input/output), which is the standard transport for MCP servers.

What are the runtime requirements?

Node.js (LTS recommended) and npm are required. The server is written in TypeScript and compiles to JavaScript.

What limits exist on task parameters?

Task descriptions are limited to 1–1024 characters, subtask descriptions to 1–512 characters, and dependency arrays to a maximum of 50 entries. The addTask and setTaskStatus tools accept up to 100 task IDs in a single call.