agent-todo-mcp

w04m1/agent-todo-mcp

3.2

If you are the rightful owner of agent-todo-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A Model Context Protocol server for AI agents to manage tasks and track progress across projects.

Tools
  1. list_projects

    List all available project workspaces

  2. switch_project

    Create new project or switch between existing ones

  3. get_project_info

    Show current project details

  4. create_todo

    Create new tasks

  5. update_todo

    Update existing tasks

  6. delete_todo

    Remove tasks

  7. list_todos

    List and filter tasks

  8. get_todo

    Get detailed task info

  9. search_todos

    Search across all tasks

  10. generate_report

    Create progress reports

  11. get_stats

    Quick statistics

Agent TODO MCP Server

A Model Context Protocol server for AI agents to manage tasks and track progress across projects.

Features

  • Create, update, and manage TODOs with detailed metadata
  • Track progress, status, priority, and dependencies
  • Explicit project isolation to prevent data mixup between workspaces
  • Search, filter, and generate comprehensive reports
  • Persistent JSON storage with complete project separation

Installation

Via npm (Recommended)

npm install -g agent-todo-mcp

From Source

git clone https://github.com/w04m1/agent-todo-mcp.git
cd agent-todo-mcp
npm install
npm run build
npm install -g .

Configuration

Add to your Claude Desktop/Cursor/VSCode/etc. config:

{
  "mcpServers": {
    "agent-todo": {
      "command": "agent-todo-mcp"
    }
  }
}

How AI Models Use This Server

When AI models interact with this MCP server, they follow this workflow:

  1. Check existing projects with list_projects
  2. Create or switch to a project with switch_project
  3. Create and manage TODOs within that project workspace

Project Management

Project Naming Best Practices

When creating projects, use descriptive names that clearly identify the workspace:

  • āœ… "my-react-app" - Good descriptive name
  • āœ… "backend-api-v2" - Clear project identifier
  • āœ… "research-ml-models" - Descriptive and specific
  • āŒ "project1" - Too generic
  • āŒ "temp" - Not descriptive

Project Isolation & Storage

Each project workspace is completely isolated. TODOs are stored in:

~/.agent-todos/
ā”œā”€ā”€ my-react-app/todos.json      # Project: "my-react-app"
ā”œā”€ā”€ backend-api-v2/todos.json    # Project: "backend-api-v2"
ā”œā”€ā”€ research-ml-models/todos.json # Project: "research-ml-models"
└── default-workspace/todos.json # Default fallback project

Architecture

  • Complete Isolation: Each project has its own TODO storage
  • Explicit Management: Projects are created explicitly via switch_project tool
  • Persistent Storage: All data persists in ~/.agent-todos/{projectId}/
  • āš ļø No Deletion: Projects cannot be deleted through the API (only individual TODOs can be deleted)

Available Tools

Project Management

  • list_projects - List all available project workspaces
  • switch_project - Create new project or switch between existing ones
  • get_project_info - Show current project details

Core Management

  • create_todo - Create new tasks
  • update_todo - Update existing tasks
  • delete_todo - Remove tasks
  • list_todos - List and filter tasks
  • get_todo - Get detailed task info

Search & Analytics

  • search_todos - Search across all tasks
  • generate_report - Create progress reports
  • get_stats - Quick statistics

TODO Structure

interface Todo {
  id: string;
  title: string;
  description?: string;
  status: "pending" | "in-progress" | "completed" | "blocked";
  priority: "low" | "medium" | "high" | "urgent";
  progress: number; // 0-100
  tags: string[];
  dependencies: string[]; // Other TODO IDs
  dueDate?: string;
  metadata: Record<string, any>;
  createdAt: string;
  updatedAt: string;
}

Development

npm run dev    # Development mode
npm run build  # Build project
npm start      # Run built server

License

MIT


Built with AI for AI 🤔