RTM MCP Server

RTM MCP Server

An MCP server that enables Claude to manage Remember The Milk tasks, lists, and notes using natural language and Smart Add syntax. It provides full API coverage for task manipulation, including priority settings, tags, and undo support.

Category
Visit Server

README

RTM MCP Server

A production-quality Model Context Protocol (MCP) server for Remember The Milk task management.

Enables Claude to manage your tasks through natural language conversation.

Features

  • Full RTM API Coverage: 30+ tools covering tasks, lists, tags, notes, and more
  • Smart Add Syntax: Natural language task creation ("Call mom ^tomorrow !1 #family")
  • Undo Support: All write operations return transaction IDs for undo
  • Async Performance: Built on httpx with connection pooling
  • Type Safety: Full Pydantic models and type hints

Installation

Using uvx (Recommended)

uvx rtm-mcp

Using pip

pip install rtm-mcp

From Source

git clone https://github.com/ljadach/rtm-mcp.git
cd rtm-mcp
uv sync

Setup

1. Get RTM API Credentials

  1. Go to RTM API Keys
  2. Create a new API key
  3. Note your API Key and Shared Secret

2. Run Setup

rtm-setup

This will:

  • Prompt for your API credentials
  • Open your browser for authorization
  • Save the auth token to ~/.config/rtm-mcp/config.json

3. Configure Claude Desktop

Add to ~/.config/claude/claude_desktop_config.json:

{
  "mcpServers": {
    "rtm": {
      "command": "uvx",
      "args": ["rtm-mcp"]
    }
  }
}

Usage

Once configured, you can ask Claude to manage your tasks:

  • "Show my tasks due today"
  • "Add a task to buy groceries tomorrow, high priority"
  • "Complete the grocery task"
  • "What high priority tasks do I have?"
  • "Move the meeting prep task to my Work list"
  • "Add a note to the project task"

Smart Add Syntax

When adding tasks, use RTM's Smart Add syntax:

Symbol Meaning Example
^ Due date ^tomorrow, ^next friday
! Priority !1 (high), !2 (medium), !3 (low)
# Tag #work, #urgent
@ Location @home, @office
= Estimate =30min, =2h
* Repeat *daily, *every monday

Example: "Review report ^friday !1 #work =1h *weekly"

Available Tools

Tasks

  • list_tasks - List tasks with filters
  • add_task - Create a new task
  • complete_task / uncomplete_task - Mark done or reopen
  • delete_task - Remove a task
  • postpone_task - Move due date by one day
  • move_task - Move to different list
  • set_task_name - Rename task
  • set_task_due_date - Change due date
  • set_task_priority - Set priority level
  • set_task_recurrence - Set repeat pattern
  • set_task_start_date - Set start date
  • set_task_estimate - Set time estimate
  • set_task_url - Attach URL
  • add_task_tags / remove_task_tags - Manage tags

Notes

  • add_note - Add note to task
  • edit_note - Edit existing note
  • delete_note - Remove note
  • get_task_notes - View all notes

Lists

  • get_lists - List all lists
  • add_list - Create new list
  • rename_list - Rename list
  • delete_list - Delete list
  • archive_list / unarchive_list - Archive management
  • set_default_list - Set default list

Utilities

  • test_connection - Test API connectivity
  • check_auth - Verify authentication
  • get_tags - List all tags
  • get_locations - List saved locations
  • get_settings - View user settings
  • get_contacts / get_groups - Contact management
  • parse_time - Parse natural language time
  • undo - Undo previous operation

Configuration

Environment Variables

RTM_API_KEY=your_api_key
RTM_SHARED_SECRET=your_shared_secret
RTM_AUTH_TOKEN=your_token

Config File

~/.config/rtm-mcp/config.json:

{
  "api_key": "your_api_key",
  "shared_secret": "your_shared_secret",
  "token": "your_token"
}

Development

# Install dev dependencies
make dev

# Run linting
make lint

# Run tests
make test

# Run with coverage
make test/coverage

# Format code
make format

Docker

docker build -t rtm-mcp .
docker run -it --rm \
  -e RTM_API_KEY \
  -e RTM_SHARED_SECRET \
  -e RTM_AUTH_TOKEN \
  rtm-mcp

Claude Desktop config for Docker:

{
  "mcpServers": {
    "rtm": {
      "command": "docker",
      "args": ["run", "-i", "--rm",
        "-e", "RTM_API_KEY",
        "-e", "RTM_SHARED_SECRET",
        "-e", "RTM_AUTH_TOKEN",
        "rtm-mcp"]
    }
  }
}

License

MIT License - see LICENSE for details.

Acknowledgments

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured