icalPal MCP Server
Enables AI assistants to interact with macOS Calendar and Reminders applications. Allows querying events, tasks, calendars, and accounts through natural language using the icalPal Ruby gem.
README
icalPal MCP Server
A Model Context Protocol (MCP) server that provides access to macOS Calendar and Reminders data via the icalPal gem.
Overview
This MCP server allows AI assistants to interact with your macOS Calendar and Reminders applications, enabling queries about events, tasks, calendars, and accounts. It uses the icalPal Ruby gem under the hood to access the Calendar and Reminders databases.
Prerequisites
- macOS system with Calendar and Reminders apps
- Ruby with the icalPal gem installed
- Python 3.8+ with FastMCP
- Full Disk Access permission for your terminal/application
Installing icalPal
gem install icalPal
Installing Python Dependencies
pip install fastmcp
Or using uv:
uv sync
Setup
1. Full Disk Access Permission
The icalPal gem requires Full Disk Access to read the Calendar and Reminders databases. Grant this permission by:
- Open System Settings > Privacy & Security > Full Disk Access
- Add your terminal application (Terminal.app, iTerm2, etc.) or the application running the MCP server
- Restart your terminal/application
2. Running the Server
Direct Python execution:
python main.py
Using Docker:
docker-compose up
The server will start on port 8000 by default, or you can configure it using environment variables:
MCP_PORT: Port number (default: 8000)MCP_TRANSPORT: Transport type (default: "sse")
Available Tools
Calendar Events
get_events- Retrieve calendar events with various filters (date range, calendars, etc.)get_events_today- Get events occurring todayget_events_now- Get events occurring right now
Tasks/Reminders
get_tasks- Retrieve tasks/reminders with filtersget_dated_tasks- Get tasks with due datesget_undated_tasks- Get tasks without due dates
Calendar Management
get_calendars- List available calendarsget_accounts- List calendar accounts
Error Handling
The server provides informative error messages for common issues:
- Permission errors: Guidance on enabling Full Disk Access
- Database access errors: Information about Calendar database location
- Invalid arguments: Clear descriptions of parameter requirements
Running in Development
# Install dependencies
uv sync
# Run the server
uv run python main.py
Docker Development
# Build and run with Docker Compose
docker-compose up --build
# Run in detached mode
docker-compose up -d
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.