gg-mcp
A Model Context Protocol (MCP) server that connects AI agents to Google Workspace (Gmail, Calendar, Drive, Docs, Sheets, and Slides).
README
Google Cloud MCP - Google Workspace MCP Server (gg-mcp)
A Model Context Protocol (MCP) server that connects AI agents to Google Workspace: Gmail, Calendar, Drive, Docs, Sheets, and Slides. Built with FastMCP.
# Install and run ā that's it
uvx gg-mcp
ļæ½ Table of Contents
- Quick Start (5 minutes)
- Available Tools
- Installation Options
- Environment Variables
- Troubleshooting
- Documentation
- Development
š Quick Start (5 minutes)
Step 1: Get Google OAuth Credentials
- Go to Google Cloud Console
- Create a project and enable OAuth consent screen (External type)
- Add required scopes (Gmail, Drive, Calendar, Docs, Sheets, Slides)
- Create OAuth 2.0 Desktop app credentials
- Copy Client ID and Client Secret
š Detailed guide ā
Step 2: Install & Run
export GOOGLE_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GOOGLE_CLIENT_SECRET="your-client-secret"
uvx gg-mcp
You'll see:
============================================================
š GOOGLE ACCOUNT AUTHENTICATION
š± Open your browser: http://localhost:3838
============================================================
Open http://localhost:3838 ā "Authorize with Google" ā Grant permissions ā
Step 3: Configure MCP Client
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"gg-mcp": {
"command": "uvx",
"args": ["gg-mcp"],
"env": {
"GOOGLE_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
"GOOGLE_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Restart Claude Desktop and the tools are ready to use! š
š Available Tools (30+)
Account
get_account_info- Get the email of the authenticated Google account
Gmail
send_email- Send an email (to, subject, body)create_gmail_label- Create a new Gmail labellist_gmail_labels- List all user-created labels
Google Calendar
list_calendar_events- List upcoming events (max_results, days_back)create_calendar_event- Create an event (summary, start_time, end_time)
Google Drive
list_drive_folders- List all folders in Google Drive (root or specific parent)search_drive- Search files by query string
Google Docs
create_document- Create a new document with optional textget_document- Get the full text content of a documentappend_to_document- Append text to document endsearch_documents- Search for documents in Driveexport_document- Export document (text, html, pdf, docx)
Google Sheets
create_spreadsheet- Create a new spreadsheetread_spreadsheet- Read data from a rangeupdate_spreadsheet- Update cells with JSON 2D arrayappend_to_spreadsheet- Append rows to spreadsheetsearch_spreadsheets- Search for spreadsheets in Driveget_spreadsheet_info- Get metadata and dimensionsclear_spreadsheet_range- Clear all values in a rangebatch_update_spreadsheet- Batch update multiple rangesadd_sheet- Add a new sheet/tabexport_spreadsheet- Export (csv, xlsx, pdf, tsv)
Google Slides
create_presentation- Create a new presentationget_presentation- Get slide metadata and contentadd_slide- Add a new slide with layout selectionadd_text_to_slide- Add a text box to slidesearch_presentations- Search for presentationsdelete_slide- Delete a slide by indexexport_presentation- Export (pdf, pptx, txt)
š Quick Start (5 minutes)
Step 1: Get Google OAuth Credentials
- Go to Google Cloud Console
- Create a project and enable OAuth consent screen (External type)
- Add required scopes (Gmail, Drive, Calendar, Docs, Sheets, Slides)
- Create OAuth 2.0 Desktop app credentials
- Copy Client ID and Client Secret
š Detailed guide ā
Step 2: Install & Run
export GOOGLE_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GOOGLE_CLIENT_SECRET="your-client-secret"
uvx gg-mcp
You'll see:
============================================================
š GOOGLE ACCOUNT AUTHENTICATION
š± Open your browser: http://localhost:3838
============================================================
Open http://localhost:3838 ā "Authorize with Google" ā Grant permissions ā
Step 3: Configure MCP Client
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"gg-mcp": {
"command": "uvx",
"args": ["gg-mcp"],
"env": {
"GOOGLE_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
"GOOGLE_CLIENT_SECRET": "your-client-secret"
}
}
}
}
š¦ Installation Options
Option A: PyPI (Recommended)
pip install gg-mcp
export GOOGLE_CLIENT_ID="..."
export GOOGLE_CLIENT_SECRET="..."
gg-mcp
Option B: From Source
git clone https://github.com/tannht/google-cloud-mcp.git
cd google-cloud-mcp
uv sync
export GOOGLE_CLIENT_ID="..."
export GOOGLE_CLIENT_SECRET="..."
uv run main.py
Option C: Docker
git clone https://github.com/tannht/google-cloud-mcp.git
cd google-cloud-mcp
docker-compose up -d --build
š Environment Variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
GOOGLE_CLIENT_ID |
Yes | ā | OAuth 2.0 Client ID |
GOOGLE_CLIENT_SECRET |
Yes | ā | OAuth 2.0 Client Secret |
GOOGLE_TOKEN_PATH |
No | .token.json |
Token file path |
GOOGLE_TOKEN_JSON |
No | ā | Token as JSON string |
AUTH_PORT |
No | 3838 |
Auth portal port |
ā Troubleshooting
| Problem | Solution |
|---|---|
403: access_denied |
Add your email to Test users in OAuth consent screen |
401: Invalid credentials |
Verify GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET |
Token expired |
Delete .token.json and re-authenticate |
| Can't access http://localhost:3838 | Port 3838 in use. Try AUTH_PORT=8080 |
403: API not enabled |
Enable APIs in Google Cloud Console |
š Documentation
- GUIDE.md - Complete user & developer guide
- MCP_CLIENTS.md - 25+ MCP client configurations
š ļø Development
git clone https://github.com/tannht/google-cloud-mcp.git
cd google-cloud-mcp
uv sync --group dev
uv run pytest -v # Run tests
š Dev setup ā
š License
MIT
š„ Contributors
- Hoang Tan (Owner)
- PubPug Assistant (Primary Developer)
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.