About Google Calendar MCP Server
Google Calendar MCP Server provides MCP tools for managing Google Calendar events. It is for users who need programmatic calendar access, with date-filtered event listing and create, update, and delete operations.
Key features
- 01List events by date range
- 02Create events with attendees
- 03Update existing events
- 04Delete calendar events
Use cases
- 01Review events within a chosen period
- 02Create meetings with attendees
- 03Change meeting times or locations
- 04Remove events that are no longer needed
MCP support
The MCP server exposes Google Calendar API event lookup and management operations as tools for MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGoogle Calendar MCP Server
A Model Context Protocol (MCP) server that provides tools for interacting with Google Calendar API. This server enables you to manage your calendar events programmatically through the MCP interface.
Features
Calendar Tools
list_events: List upcoming calendar events with date range filteringcreate_event: Create new calendar events with attendeesupdate_event: Update existing calendar eventsdelete_event: Delete calendar events
Prerequisites
- Node.js: Install Node.js version 14 or higher
- Google Cloud Console Setup:
- Go to Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Calendar API:
- Go to "APIs & Services" > "Library"
- Search for and enable "Google Calendar API"
- Set up OAuth 2.0 credentials:
- Go to "APIs & Services" > "Credentials"
- Click "Create Credentials" > "OAuth client ID"
- Choose "Web application"
- Set "Authorized redirect URIs" to include:
http://localhost:3000/code - Note down the Client ID and Client Secret
Setup Instructions
-
Clone and Install:
git clone https://github.com/yourusername/google-calendar-mcp-server.git cd google-calendar-mcp-server npm install -
Create OAuth Credentials: Create a
credentials.jsonfile in the root directory:{ "web": { "client_id": "YOUR_CLIENT_ID", "client_secret": "YOUR_CLIENT_SECRET", "redirect_uris": ["http://localhost:3000/code"], "auth_uri": "https://accounts.google.com/o/oauth2/auth", "token_uri": "https://oauth2.googleapis.com/token" } } -
Get Refresh Token:
node get-refresh-token.jsThis will:
- Open your browser for Google OAuth authentication
- Request the following permissions:
https://www.googleapis.com/auth/calendar
- Save the credentials to
token.json - Display the refresh token in the console
-
Configure MCP Settings: Add the server configuration to your MCP settings file:
- For VSCode Claude extension:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - For Claude desktop app:
~/Library/Application Support/Claude/claude_desktop_config.json
Add this to the
mcpServersobject:{ "mcpServers": { "google-calendar": { "command": "node", "args": ["/path/to/google-calendar-server/build/index.js"], "env": { "GOOGLE_ACCESS_TOKEN": "your_access_token", } } } } - For VSCode Claude extension:
-
Build and Run:
npm run build
Usage Examples
Calendar Operations
-
List Events:
{ "maxResults": 10, "timeMin": "2024-01-01T00:00:00Z", "timeMax": "2024-12-31T23:59:59Z" } -
Create Event:
{ "summary": "Team Meeting", "location": "Conference Room", "description": "Weekly sync-up", "start": "2024-01-24T10:00:00Z", "end": "2024-01-24T11:00:00Z", "attendees": ["[email protected]"] } -
Update Event:
{ "eventId": "event_id", "summary": "Updated Meeting", "location": "Virtual", "description": "Rescheduled weekly sync-up", "start": "2024-01-25T10:00:00Z", "end": "2024-01-25T11:00:00Z" } -
Delete Event:
{ "eventId": "event_id" }
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.