dav-mcp

by PhilflowIO

28 stars
234 downloads
Not rated
GitHub

About

Turn any calendar, contact book, or task list into an AI-orchestrated system. Platform-independent via CalDAV/CardDAV — works with Nextcloud, Baikal, Radicale, Fastmail, and any standards-compliant DAV server. 26 tools with field-agnostic updates.

Details

Author
PhilflowIO
GitHub stars
28
Downloads
234
Categories
Productivity, Other

- 26 tools: full CRUD for calendars, contacts, and tasks
- Field‑based updates on all RFC properties plus custom fields
- Server‑side filtering for efficient queries (calendar_query, addressbook_query, todo_query)
- Multi‑provider: works with any CalDAV/CardDAV server
- OAuth2 authentication for Google Calendar
- Input validation, rate limiting, bearer auth, and no credential storage

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name dav-mcp
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Configure dav-mcp by setting environment variables (CALDAV_SERVER_URL, CALDAV_USERNAME, CALDAV_PASSWORD) and running it with npx. For local use with Claude Desktop or Cursor, add the command to the MCP config file; for remote use with n8n, start the HTTP server with a bearer token. A Docker setup is also available via docker-compose up.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "dav-mcp": {
            "dav-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "dav-mcp"
                ],
                "env": {
                    "CALDAV_SERVER_URL": "https://dav.example.com",
                    "CALDAV_USERNAME": "your_username",
                    "CALDAV_PASSWORD": "your_password"
                }
            }
        }
    }
}

McpServers

{
    "dav-mcp": {
        "command": "npx",
        "args": [
            "-y",
            "dav-mcp"
        ],
        "env": {
            "CALDAV_SERVER_URL": "https://dav.example.com",
            "CALDAV_USERNAME": "your_username",
            "CALDAV_PASSWORD": "your_password"
        }
    }
}

dav-mcp

Give your AI agents the power of organization — Transform them into orchestrating assistants managing calendars, contacts, and tasks.

Built on 26 production-ready tools spanning CalDAV, CardDAV, and VTODO protocols.

License: MIT
npm version

---

Quick Start

Claude Desktop / Cursor (Local)

Add to your MCP config file:

{
  "mcpServers": {
    "dav-mcp": {
      "command": "npx",
      "args": ["-y", "dav-mcp"],
      "env": {
        "CALDAV_SERVER_URL": "https://dav.example.com",
        "CALDAV_USERNAME": "your_username",
        "CALDAV_PASSWORD": "your_password"
      }
    }
  }
}

Config file locations:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json

Restart Claude Desktop after adding the configuration.

---

n8n (Remote HTTP)

Start the HTTP server:

CALDAV_SERVER_URL=https://dav.example.com \
CALDAV_USERNAME=your_username \
CALDAV_PASSWORD=your_password \
BEARER_TOKEN=your-secret-token \
npx dav-mcp --http

Then in n8n:
1. Add AI Agent node
2. Add MCP Client Tool node and connect to AI Agent
3. Configure:
- MCP Endpoint: http://localhost:3000/mcp
- Authentication: Bearer
- Token: your-secret-token

Custom port:

npx dav-mcp --http --port=8080

---

Docker

```bash
git clone https://github.com/PhilflowIO/dav-mcp.git
cd dav-mcp
cp .env.example .env

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.