google-workspace-mcp
MCP server enabling Cursor to interact with Google Workspace services including Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, and People via natural language.
README
Google Workspace MCP Server for Cursor
An MCP (Model Context Protocol) server that provides Cursor with tools to interact with Google Workspace: Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, and People.
Repository: github.com/Dave-Nguyen-PM/google-workplace-mcp
Prerequisites
- Node.js >= 20
- A Google Cloud project with OAuth 2.0 credentials
GCP Setup
- Go to Google Cloud Console
- Create a new project (or use an existing one)
- Enable these APIs:
- Gmail API
- Google Calendar API
- Google Drive API
- Google Docs API
- Google Sheets API
- Google Slides API
- Google Chat API
- People API
- Go to APIs & Services > OAuth consent screen and configure it
- Go to APIs & Services > Credentials and create an OAuth 2.0 Client ID (type: Desktop app)
- Download the JSON file
Installation
cd /path/to/google-workplace-mcp
npm install
npm run build
Configuration
Place the downloaded OAuth credentials file in one of these locations:
./credentials.jsonin the project root~/.google-workspace-mcp/credentials.json- Set
GOOGLE_CREDENTIALS_PATHenvironment variable
Add to your Cursor MCP settings (~/.cursor/mcp.json):
{
"mcpServers": {
"google-workspace": {
"command": "node",
"args": ["/path/to/google-workplace-mcp/dist/index.js"],
"env": {
"GOOGLE_CREDENTIALS_PATH": "/path/to/credentials.json"
}
}
}
}
First Run
On the first request that requires Google auth, a browser window will open for OAuth consent. After authorizing, tokens are cached at ~/.google-workspace-mcp/tokens.json and auto-refreshed.
Tools (57 total)
| Domain | Tools | Access |
|---|---|---|
| Auth | auth_clear, auth_refreshToken |
- |
| Time | time_getCurrentDate, time_getCurrentTime, time_getTimeZone |
Read |
| Drive | drive_search, drive_findFolder, drive_createFolder, drive_downloadFile, drive_moveFile, drive_trashFile, drive_renameFile, drive_getComments |
Read/Write |
| Docs | docs_create, docs_getText, docs_writeText, docs_replaceText, docs_formatText, docs_getSuggestions |
Read/Write |
| Sheets | sheets_getText, sheets_getRange, sheets_find, sheets_getMetadata |
Read |
| Slides | slides_getText, slides_find, slides_getMetadata, slides_getImages, slides_getSlideThumbnail |
Read |
| Calendar | calendar_list, calendar_createEvent, calendar_listEvents, calendar_getEvent, calendar_findFreeTime, calendar_updateEvent, calendar_respondToEvent, calendar_deleteEvent |
Read/Write |
| Gmail | gmail_search, gmail_get, gmail_downloadAttachment, gmail_modify, gmail_batchModify, gmail_modifyThread, gmail_send, gmail_createDraft, gmail_sendDraft, gmail_listLabels, gmail_createLabel |
Read/Write |
| Chat | chat_listSpaces, chat_findSpaceByName, chat_sendMessage, chat_getMessages, chat_sendDm, chat_findDmByEmail, chat_listThreads, chat_setUpSpace |
Read/Write |
| People | people_getUserProfile, people_getMe, people_getUserRelations |
Read |
Debug Mode
Run with --debug to enable file logging to ~/.google-workspace-mcp/debug.log:
{
"mcpServers": {
"google-workspace": {
"command": "node",
"args": ["/path/to/dist/index.js", "--debug"]
}
}
}
Development
npm run dev # Watch mode (rebuilds on changes)
npm run build # Production build
npm start # Run the server directly
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.