
Todo Markdown
Manages todo lists stored in markdown files with standard checkbox format. Tracks each item with persistent UUIDs while maintaining human-readable format.
Provides todo list management with markdown file storage, offering CRUD operations for listing, adding, updating, and deleting tasks with persistent UUID tracking and human-readable checkbox format.
What it does
- List all todo items from markdown file
- Add new todo items with descriptions
- Update existing todo item status and text
- Delete specific todo items by ID
- Clear all completed tasks at once
Best for
About Todo Markdown
Todo Markdown is a community-built MCP server published by danjdewhurst that provides AI assistants with tools and capabilities via the Model Context Protocol. Manage your tasks efficiently with Todo Markdown—CRUD todo lists stored in markdown files, featuring UUID tracking and c It is categorized under productivity. This server exposes 5 tools that AI clients can invoke during conversations and coding sessions.
How to install
You can install Todo Markdown in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
License
Todo Markdown is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Tools (5)
List all todos from the markdown file
Add a new todo item
Update an existing todo item
Delete a todo item
Remove all completed todo items
Todo Markdown MCP Server
An MCP (Model Context Protocol) server that provides todo list functionality backed by a simple markdown file. This server allows AI assistants to manage todo items in a standardized markdown format.
Features
- Markdown-based storage: Todos are stored in a simple
todo.mdfile using standard checkbox syntax - Full CRUD operations: Create, read, update, and delete todo items
- Persistent IDs: Each todo has a unique identifier for reliable updates
- MCP compliance: Follows the Model Context Protocol specification
- TypeScript: Fully typed implementation with comprehensive error handling
- Testing: Complete test suite with Vitest
Installation
From NPM
npm install -g @danjdewhurst/todo-md-mcp
Local Development
- Clone this repository:
git clone https://github.com/danjdewhurst/todo-md-mcp.git cd todo-md-mcp - Install dependencies:
npm install - Build the project:
npm run build
Usage
With Claude Desktop
Add this server to your Claude Desktop configuration:
{
"mcpServers": {
"todo-md": {
"command": "node",
"args": ["/path/to/todo-md-mcp/dist/index.js"]
}
}
}
Or if installed globally via NPM:
{
"mcpServers": {
"todo-md": {
"command": "npx",
"args": ["@danjdewhurst/todo-md-mcp"]
}
}
}
Configuring Todo File Location
By default, the server creates a todo.md file in the current working directory. When using Claude Desktop, this might be a system directory where you don't have write permissions. To specify a custom location for your todo file, use the TODO_FILE_PATH environment variable:
{
"mcpServers": {
"todo-md": {
"command": "npx",
"args": ["@danjdewhurst/todo-md-mcp"],
"env": {
"TODO_FILE_PATH": "/Users/yourname/Documents/todo.md"
}
}
}
}
This solves the common "read-only file system" error by ensuring the todo file is created in a location where you have write permissions.
Recommended locations:
~/Documents/todo.md- Your Documents folder~/Desktop/todo.md- Your Desktop/path/to/your/project/todo.md- Within a specific project
Important: Make sure the directory exists and you have write permissions to the specified location.
Available Tools
The server provides the following MCP tools:
list_todos
Lists all todo items from the markdown file.
Parameters: None
Returns: JSON object with todos array and summary statistics
add_todo
Adds a new todo item.
Parameters:
text(string, required): The todo item text
Returns: The created todo item with generated ID
update_todo
Updates an existing todo item.
Parameters:
id(string, required): The todo item IDtext(string, optional): New text for the todocompleted(boolean, optional): Mark as completed/incomplete
Returns: The updated todo item
delete_todo
Deletes a todo item.
Parameters:
id(string, required): The todo item ID to delete
Returns: Success confirmation
clear_completed
Removes all completed todo items.
Parameters: None
Returns: Number of items cleared
File Format
The server manages a todo.md file in your project root with the following format:
# Todo List
- [ ] First incomplete task <!-- id:550e8400-e29b-41d4-a716-446655440000 -->
- [x] Completed task <!-- id:6ba7b810-9dad-11d1-80b4-00c04fd430c8 -->
- [ ] Another task <!-- id:6ba7b811-9dad-11d1-80b4-00c04fd430c8 -->
<!-- Generated by MCP Todo Server -->
Each todo item includes:
- Standard markdown checkbox syntax (
- [ ]or- [x]) - The todo text
- A hidden HTML comment with a unique ID for tracking
Development
Scripts
npm run build- Build the TypeScript projectnpm run dev- Build and run the servernpm run watch- Watch for changes and rebuildnpm test- Run the test suitenpm run test:watch- Run tests in watch modenpm run lint- Run ESLintnpm run format- Format code with Prettier
Testing
The project includes comprehensive tests covering all functionality:
npm test
Tests cover:
- Markdown parsing and generation
- CRUD operations
- Error handling
- File management
Project Structure
todo-md-mcp/
├── src/
│ ├── index.ts # Main MCP server implementation
│ ├── todoManager.ts # Todo CRUD operations and markdown parsing
│ └── types.ts # TypeScript type definitions
├── tests/
│ └── todoManager.test.ts # Test suite
├── dist/ # Built JavaScript files
├── package.json
├── tsconfig.json
├── .eslintrc.json
├── .prettierrc
├── vitest.config.ts
└── README.md
Requirements
- Node.js 18 or higher
- An MCP-compatible client (like Claude Desktop)
License
MIT
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Run the test suite
- Submit a pull request
Model Context Protocol
This server implements the Model Context Protocol (MCP), an open protocol that standardizes how applications provide context to Large Language Models. MCP enables secure, controlled access to local and remote resources.
For more information about MCP, visit the official documentation.
Alternatives
Related Skills
Browse all skillsThis skill fetches open tasks assigned to the user from the Linear API and generates a markdown todo list file in the project root. This skill should be used when the user asks about their work items, wants to see what they need to work on, or requests to load/sync their Linear tasks. Requires Python 3.7+, requests, mdutils, and python-dotenv packages. Requires LINEAR_API_KEY in .env file.
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
Comprehensive guide for Slidev - a web-based presentation framework for developers. Covers Markdown syntax, layouts, components, animations, theming, and exporting. Use this skill when creating or working with developer presentations using Slidev.
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists