MCP Task Manager Server
The MCP Task Manager Server is a backend tool for managing tasks within projects using a SQLite database. It provides these capabilities:
Project Management: Create, delete, and export/import projects as JSON
Task Management: Add, list, show, update, and delete tasks with descriptions, priorities, and dependencies
Task Organization: Break down tasks into subtasks and manage their relationships
Status Tracking: Update and filter tasks by their completion status
Workflow Optimization: Identify the next actionable task based on dependencies, status, priority, and creation date
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 Task Manager Serveradd a high priority task to finish the quarterly report by Friday"
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 Task Manager Server
A local Model Context Protocol (MCP) server providing backend tools for client-driven project and task management using a SQLite database.
Overview
This server acts as a persistent backend for local MCP clients (like AI agents or scripts) that need to manage structured task data within distinct projects. It handles data storage and provides a standardized set of tools for interaction, while the strategic workflow logic resides within the client.
Key Features:
Project-Based: Tasks are organized within distinct projects.
SQLite Persistence: Uses a local SQLite file (
./data/taskmanager.dbby default) for simple, self-contained data storage.Client-Driven: Provides tools for clients; does not dictate workflow.
MCP Compliant: Adheres to the Model Context Protocol for tool definition and communication.
Task Management: Supports creating projects, adding tasks, listing/showing tasks, updating status, expanding tasks into subtasks, and identifying the next actionable task.
Import/Export: Allows exporting project data to JSON and importing from JSON to create new projects.
Related MCP server: MATRIX
Implemented MCP Tools
The following tools are available for MCP clients:
createProject:Description: Creates a new, empty project.
Params:
projectName(string, optional, max 255)Returns:
{ project_id: string }
addTask:Description: Adds a new task to a project.
Params:
project_id(string, required, UUID),description(string, required, 1-1024),dependencies(string[], optional, max 50),priority(enum 'high'|'medium'|'low', optional, default 'medium'),status(enum 'todo'|'in-progress'|'review'|'done', optional, default 'todo')Returns: Full
TaskDataobject of the created task.
listTasks:Description: Lists tasks for a project, with optional filtering and subtask inclusion.
Params:
project_id(string, required, UUID),status(enum 'todo'|'in-progress'|'review'|'done', optional),include_subtasks(boolean, optional, default false)Returns: Array of
TaskDataorStructuredTaskDataobjects.
showTask:Description: Retrieves full details for a specific task, including dependencies and direct subtasks.
Params:
project_id(string, required, UUID),task_id(string, required)Returns:
FullTaskDataobject.
setTaskStatus:Description: Updates the status of one or more tasks.
Params:
project_id(string, required, UUID),task_ids(string[], required, 1-100),status(enum 'todo'|'in-progress'|'review'|'done', required)Returns:
{ success: true, updated_count: number }
expandTask:Description: Breaks a parent task into subtasks, optionally replacing existing ones.
Params:
project_id(string, required, UUID),task_id(string, required),subtask_descriptions(string[], required, 1-20, each 1-512),force(boolean, optional, default false)Returns: Updated parent
FullTaskDataobject including new subtasks.
getNextTask:Description: Identifies the next actionable task based on status ('todo'), dependencies ('done'), priority, and creation date.
Params:
project_id(string, required, UUID)Returns:
FullTaskDataobject of the next task, ornullif none are ready.
exportProject:Description: Exports complete project data as a JSON string.
Params:
project_id(string, required, UUID),format(enum 'json', optional, default 'json')Returns: JSON string representing the project.
importProject:Description: Creates a new project from an exported JSON string.
Params:
project_data(string, required, JSON),new_project_name(string, optional, max 255)Returns:
{ project_id: string }of the newly created project.
updateTask:Description: Updates specific details (description, priority, dependencies) of an existing task.
Params:
project_id(string, required, UUID),task_id(string, required, UUID),description(string, optional, 1-1024),priority(enum 'high'|'medium'|'low', optional),dependencies(string[], optional, max 50, replaces existing)Returns: Updated
FullTaskDataobject.
deleteTask:Description: Deletes one or more tasks (and their subtasks/dependency links via cascade).
Params:
project_id(string, required, UUID),task_ids(string[], required, 1-100)Returns:
{ success: true, deleted_count: number }
deleteProject:Description: Permanently deletes a project and ALL associated data. Use with caution!
Params:
project_id(string, required, UUID)Returns:
{ success: true }
(Note: Refer to the corresponding src/tools/*Params.ts files for detailed Zod schemas and parameter descriptions.)
Getting Started
Prerequisites: Node.js (LTS recommended), npm.
Install Dependencies:
npm installRun in Development Mode: (Uses
ts-nodeandnodemonfor auto-reloading)npm run devThe server will connect via stdio. Logs (JSON format) will be printed to stderr. The SQLite database will be created/updated in
./data/taskmanager.db.Build for Production:
npm run buildRun Production Build:
npm start
Configuration
Database Path: The location of the SQLite database file can be overridden by setting the
DATABASE_PATHenvironment variable. The default is./data/taskmanager.db.Log Level: The logging level can be set using the
LOG_LEVELenvironment variable (e.g.,debug,info,warn,error). The default isinfo.
Project Structure
/src: Source code./config: Configuration management./db: Database manager and schema (schema.sql)./repositories: Data access layer (SQLite interaction)./services: Core business logic./tools: MCP tool definitions (*Params.ts) and implementation (*Tool.ts)./types: Shared TypeScript interfaces (currently minimal, mostly in repos/services)./utils: Logging, custom errors, etc.createServer.ts: Server instance creation.server.ts: Main application entry point.
/dist: Compiled JavaScript output./docs: Project documentation (PRD, Feature Specs, RFC)./data: Default location for the SQLite database file (created automatically).tasks.md: Manual task tracking file for development.Config files (
package.json,tsconfig.json,.eslintrc.json, etc.)
Linting and Formatting
Lint:
npm run lintFormat:
npm run format
(Code is automatically linted/formatted on commit via Husky/lint-staged).
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 Connectors
Project management MCP for AI agents with safe task reads and writes.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing AI assistants with comprehensive project, task, and subtask management capabilities with project-specific storage.293888MIT
- AlicenseNot gradedqualityBmaintenanceA local, project-scoped requirement management MCP server that enables AI agents to manage tasks and requirements via SQLite.18MIT
- FlicenseBqualityCmaintenanceA Model Context Protocol server implementing a Getting Things Done assistant with tools for tasks, projects, inbox, next actions, and statistics. Supports local SQLite and Databricks deployment.17
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server for intelligent task management in AI-powered development environments, providing file-based storage, dependency management with cycle detection, and an interactive CLI.14MIT
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/bsmi021/mcp-task-manager-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server