Super Todo MCP App
A todo list manager for Creature with interactive UI, batch operations, full-text search, and markdown descriptions, enabling natural language task management.
README
Super Todo MCP App
A powerful todo list manager for Creature with an interactive UI and batch operations support. Built as an MCP App (Model Context Protocol Application) with full-text search and markdown descriptions.
Features
- Interactive UI - Beautiful, real-time todo list interface displayed in Creature
- Batch Operations - Add, toggle, or remove multiple todos in a single command
- Full-Text Search - Fast search powered by SQLite FTS5
- Markdown Support - Add rich descriptions to your todos with markdown formatting
- Persistent Storage - Todos are saved and persist across sessions
- AI-Friendly - Designed to work seamlessly with Creature's AI agent
Installation
Quick Install for Creature Users
Install directly from GitHub:
npm install -g git+https://github.com/garethmcc/super-todo-mcp.git
Then add to your Creature MCP configuration:
{
"mcpServers": {
"super-todo": {
"command": "super-todo-mcp",
"args": []
}
}
}
Manual Installation
# Clone the repository
git clone https://github.com/garethmcc/super-todo-mcp.git
cd super-todo-mcp
# Install dependencies
npm install
# Build the app
npm run build
Then add to your Creature MCP config:
{
"mcpServers": {
"super-todo": {
"command": "node",
"args": ["/path/to/super-todo-mcp/dist/server/index.js"]
}
}
}
From Creature Registry (Coming Soon)
Once submitted to the Creature registry, users will be able to:
- Open Creature
- Go to Settings ā MCP Apps
- Search for "Super Todo"
- Click "Install"
Usage
Basic Commands
Once installed, you can interact with Super Todo through Creature's AI:
View your todos:
Show me my todo list
Add todos:
Add these todos: "Buy groceries", "Call dentist", "Finish report"
Toggle completion:
Mark the first todo as complete
Remove todos:
Delete all completed todos
Search todos:
Find all todos about "meeting"
Available Tools
The MCP App provides the following tools that Creature's AI can use:
todos_list- Display all todos in the interactive list UItodos_add- Create one or more todo itemstodos_toggle- Toggle completion status for one or more todostodos_remove- Delete one or more todo itemstodos_update_description- Add or update markdown descriptionstodos_search- Full-text search across all todos
UI Features
The interactive todo list includes:
- ā Check/uncheck todos with a click
- š View and edit markdown descriptions
- š Real-time filtering and search
- š Todo count and progress tracking
- šØ Clean, modern interface
Development
Setup
# Install dependencies
npm install
# Run in development mode (with hot reload)
npm run dev
# Type checking
npm run typecheck
Project Structure
super-todo-mcp/
āāā src/
ā āāā server/ # MCP server code
ā ā āāā index.ts # Main app entry point
ā ā āāā tools/ # Tool implementations
ā ā āāā lib/ # Utilities and types
ā āāā ui/ # React UI components
ā āāā app.tsx # Main UI component
ā āāā styles.css # Styling
āāā dist/ # Built output
āāā package.json
āāā tsconfig.json
Building
# Build both UI and server
npm run build
# Build UI only
npm run build:ui
# Build server only
npm run build:server
Testing Locally with Creature
-
Start the dev server:
npm run dev -
In Creature, create a Dev MCP project pointing to
http://localhost:3100/mcp -
Make changes to the code - the UI will hot-reload automatically
Configuration
Environment Variables
MCP_PORTorPORT- Server port (default: 3005)
Data Storage
Todos are stored using Creature's persistent storage system. Each project has its own isolated todo list.
Requirements
- Node.js 18 or higher
- Creature desktop application
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Changelog
See CHANGELOG.md for a list of changes.
Support
- Issues: Report bugs or request features on GitHub Issues
- Discussions: Join the Creature community for questions and discussions
- Documentation: Visit Creature Docs for more information
Acknowledgments
Built with:
- open-mcp-app - MCP App framework
- React - UI framework
- TypeScript - Type safety
- SQLite FTS5 - Full-text search
Made with ā¤ļø for the Creature community
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.
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.
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.
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.