agent-todo-mcp
A Model Context Protocol server for AI agents to manage tasks and track progress across projects, with features like project isolation, search, and reporting.
README
Agent TODO MCP Server
Now all editors have this feature so yep...
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:
- Check existing projects with
list_projects - Create or switch to a project with
switch_project - 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:
- ✅
"my-react-app"- Good descriptive name - ✅
"backend-api-v2"- Clear project identifier - ✅
"research-ml-models"- Descriptive and specific - ❌
"project1"- Too generic - ❌
"temp"- Not descriptive
Project Isolation & Storage
Each project workspace is completely isolated. TODOs are stored in:
~/.agent-todos/
├── my-react-app/todos.json # Project: "my-react-app"
├── backend-api-v2/todos.json # Project: "backend-api-v2"
├── 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_projecttool - Persistent Storage: All data persists in
~/.agent-todos/{projectId}/ - ⚠️ 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 workspacesswitch_project- Create new project or switch between existing onesget_project_info- Show current project details
Core Management
create_todo- Create new tasksupdate_todo- Update existing tasksdelete_todo- Remove taskslist_todos- List and filter tasksget_todo- Get detailed task info
Search & Analytics
search_todos- Search across all tasksgenerate_report- Create progress reportsget_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 🤡
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.