CalDAV MCP Server
Enables CRUD operations for calendar events, journal entries, and todos on any CalDAV server (like Radicale) through the Model Communication Protocol.
README
MCP CalDAV STDIO Application
A Python-based MCP (Model Communication Protocol) application that provides CRUD operations for events, journals, and todos using the caldav Python library.
Dependencies
This application requires the following Python packages:
caldav- For CalDAV protocol supportpython-dateutil- For date/time parsing and manipulation
These dependencies are automatically managed through the package configuration.
Installation with uv
This application can be installed and run using uv or uvx:
Using uvx (no installation needed)
uvx caldav-mcp
Using uv to install
uv pip install caldav-mcp
uvx caldav-mcp
From source
git clone https://github.com/example/caldav-mcp.git
cd caldav-mcp
uv pip install -e .
uvx caldav-mcp
Direct usage with uvx from GitHub
uvx github:example/caldav-mcp
Features
- MCP Protocol Support: Communicates over STDIO using the Model Communication Protocol
- CalDAV Integration: Connects to any CalDAV server (like Radicale)
- Full CRUD Operations: Create, Read, Update, and Delete for events, journals, and todos
- Standard Data Models: Well-defined models for events, journals, and todos
- Error Handling: Comprehensive error handling and logging
- Configuration Management: Flexible configuration via files and environment variables
Architecture
┌─────────────────┐ ┌──────────────────┐ ┌──────────────────┐
│ MCP Client │ │ MCP CalDAV │ │ CalDAV Server │
│ │ │ Application │ │ │
│ STDIO Input │───▶│ (this app) │───▶│ (e.g. Radicale) │
│ JSON Messages │ │ │ │ │
│ │◀───│ │◀───│ │
│ STDIO Output │ │ │ │ │
└─────────────────┘ └──────────────────┘ └──────────────────┘
Installation
- Clone or download this repository
- Install dependencies:
pip install -r requirements.txt
Configuration
The application supports configuration through:
- Environment variables
- Configuration file (
config/settings.json)
Environment Variables
CALDAV_SERVER_URL: CalDAV server URL (default:http://localhost:5232)CALDAV_USERNAME: Username for authentication (default:user)CALDAV_PASSWORD: Password for authentication (default: ``)CALDAV_USE_SSL: Whether to use SSL (default:true)LOG_LEVEL: Logging level (default:INFO)
Configuration File
Create config/settings.json:
{
"server_url": "http://localhost:5232",
"username": "user",
"password": "",
"use_ssl": true,
"log_level": "INFO"
}
Usage
Run the application:
python main.py
The application will listen on STDIO for MCP protocol messages. It supports the following methods:
Event Operations
caldav.event.create: Create a new eventcaldav.event.read: Read an existing eventcaldav.event.update: Update an existing eventcaldav.event.delete: Delete an eventcaldav.event.list: List all events
Journal Operations
caldav.journal.create: Create a new journal entrycaldav.journal.read: Read an existing journal entrycaldav.journal.update: Update an existing journal entrycaldav.journal.delete: Delete a journal entrycaldav.journal.list: List all journal entries
Todo Operations
caldav.todo.create: Create a new todo itemcaldav.todo.read: Read an existing todo itemcaldav.todo.update: Update an existing todo itemcaldav.todo.delete: Delete a todo itemcaldav.todo.list: List all todo items
Example Request
{
"jsonrpc": "2.0",
"id": "1",
"method": "caldav.event.create",
"params": {
"title": "Team Meeting",
"description": "Weekly team sync",
"start_time": "2023-10-15T10:00:00",
"end_time": "2023-10-15T11:00:00",
"location": "Conference Room A"
}
}
Example Response
{
"jsonrpc": "2.0",
"id": "1",
"result": {
"id": "event-12345",
"status": "created"
}
}
Development
Project Structure
caldav-mcp/
├── main.py # Main application entry point
├── requirements.txt # Python dependencies
├── config/ # Configuration files
│ └── settings.json # Application settings
├── src/ # Source code
│ ├── __init__.py
│ ├── caldav_client.py # CalDAV connection and operations
│ ├── models/ # Data models
│ │ ├── __init__.py
│ │ ├── event.py # Event data model
│ │ ├── journal.py # Journal data model
│ │ └── todo.py # Todo data model
│ ├── operations/ # CRUD operations
│ │ ├── __init__.py
│ │ ├── event_ops.py # Event CRUD operations
│ │ ├── journal_ops.py # Journal CRUD operations
│ │ └── todo_ops.py # Todo CRUD operations
│ ├── stdio_interface.py # MCP STDIO protocol implementation
│ ├── config_manager.py # Configuration management
│ └── error_handler.py # Error handling and logging
└── docs/ # Documentation
├── architecture.md
├── project_structure.md
├── data_models.md
└── mcp_protocol.md
License
MIT
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.