🚀 Google Workspace MCP Server
This is a production-ready MCP server that integrates all major Google Workspace services with AI assistants. It offers full natural language control over Google Calendar, Drive, Gmail, Docs, Sheets, Slides, Forms, Tasks, and Chat through all MCP clients, AI assistants, and developer tools.
📺 See it in action
A quick plug for AI-Enhanced Docs
But why?
This README was written with AI assistance. As a solo dev building open source tools that many may never see outside use, comprehensive documentation often wouldn't happen without AI help. Using agentic dev tools like Roo & Claude Code that understand the entire codebase, AI doesn't just regurgitate generic content - it extracts real implementation details and creates accurate, specific documentation. In this case, Sonnet 4 took a pass & a human (me) verified them on 7/10/25.
🚀 Quick Start
1. One-Click Claude Desktop Install (Recommended)
- Download: Grab the latest
google_workspace_mcp.dxt
from the “Releases” page.
- Install: Double-click the file – Claude Desktop opens and prompts you to Install.
- Configure: In Claude Desktop → Settings → Extensions → Google Workspace MCP, paste your Google OAuth credentials.
- Use it: Start a new Claude chat and call any Google Workspace tool.
⚠️ Important Note
Desktop Extensions (.dxt
) bundle the server, dependencies, and manifest so users can go from download to a working MCP in one click – no terminal, no JSON editing, no version conflicts.
Required Configuration
Environment - you will configure these in Claude itself, see screenshot:
Property |
Details |
GOOGLE_OAUTH_CLIENT_ID |
OAuth client ID from Google Cloud |
GOOGLE_OAUTH_CLIENT_SECRET |
OAuth client secret |
USER_GOOGLE_EMAIL (optional) |
Default email for single-user auth |
OAUTHLIB_INSECURE_TRANSPORT=1 |
Development only (allows http:// redirect) |
Claude Desktop stores these securely in the OS keychain; set them once in the extension pane.
2. Advanced / Cross-Platform Installation
If you’re developing, deploying to servers, or using another MCP-capable client, keep reading.
Instant CLI (uvx)
export GOOGLE_OAUTH_CLIENT_ID="xxx"
export GOOGLE_OAUTH_CLIENT_SECRET="yyy"
uvx workspace-mcp --tools gmail drive calendar
⚠️ Important Note
Run instantly without manual installation - you must configure OAuth credentials when using uvx. You can use either environment variables (recommended for production) or set the GOOGLE_CLIENT_SECRET_PATH
(or legacy GOOGLE_CLIENT_SECRETS
) environment variable to point to your client_secret.json
file.
export GOOGLE_OAUTH_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GOOGLE_OAUTH_CLIENT_SECRET="your-client-secret"
uvx workspace-mcp
uvx workspace-mcp --tools gmail drive calendar tasks
uvx workspace-mcp --transport streamable-http
Requires Python 3.11+ and uvx. The package is available on PyPI.
Development Installation
For development or customization:
git clone https://github.com/taylorwilsdon/google_workspace_mcp.git
cd google_workspace_mcp
uv run main.py
Prerequisites
- Python 3.11+
- uvx (for instant installation) or uv (for development)
- Google Cloud Project with OAuth 2.0 credentials
Configuration
-
Google Cloud Setup:
-
Create OAuth 2.0 credentials (web application) in Google Cloud Console.
-
Enable APIs: Calendar, Drive, Gmail, Docs, Sheets, Slides, Forms, Tasks, Chat.
-
Add redirect URI: http://localhost:8000/oauth2callback
.
-
Configure credentials using one of these methods:
Option A: Environment Variables (Recommended for Production)
export GOOGLE_OAUTH_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GOOGLE_OAUTH_CLIENT_SECRET="your-client-secret"
export GOOGLE_OAUTH_REDIRECT_URI="http://localhost:8000/oauth2callback"
Option B: File-based (Traditional)
- Download credentials as
client_secret.json
in project root.
- To use a different location, set
GOOGLE_CLIENT_SECRET_PATH
(or legacy GOOGLE_CLIENT_SECRETS
) environment variable with the file path.
Credential Loading Priority:
- Environment variables (
GOOGLE_OAUTH_CLIENT_ID
, GOOGLE_OAUTH_CLIENT_SECRET
).
- File specified by
GOOGLE_CLIENT_SECRET_PATH
or GOOGLE_CLIENT_SECRETS
environment variable.
- Default file (
client_secret.json
in project root).
💡 Usage Tip
Using environment variables has many advantages, such as containerized deployments (Docker, Kubernetes), cloud platforms (Heroku, Railway, etc.), CI/CD pipelines, no secrets in version control, and easy credential rotation.
-
Environment:
export OAUTHLIB_INSECURE_TRANSPORT=1
export USER_GOOGLE_EMAIL=your.email@gmail.com
-
Server Configuration:
The server's base URL and port can be customized using environment variables:
WORKSPACE_MCP_BASE_URI
: Sets the base URI for the server (default: http://localhost). This affects the server_url
used to construct the default OAUTH_REDIRECT_URI
if GOOGLE_OAUTH_REDIRECT_URI
is not set.
WORKSPACE_MCP_PORT
: Sets the port the server listens on (default: 8000). This affects the server_url, port, and OAUTH_REDIRECT_URI.
USER_GOOGLE_EMAIL
: Optional default email for authentication flows. If set, the LLM won't need to specify your email when calling start_google_auth
.
GOOGLE_OAUTH_REDIRECT_URI
: Sets an override for OAuth redirect specifically, must include a full address (i.e. include port if necessary). Use this if you want to run your OAuth redirect separately from the MCP. This is not recommended outside of very specific cases.
Start the Server
uv run main.py
uv run main.py --transport streamable-http
uv run main.py --single-user
uv run main.py --tools gmail drive calendar tasks
uv run main.py --tools sheets docs
uv run main.py --single-user --tools gmail
docker build -t workspace-mcp .
docker run -p 8000:8000 -v $(pwd):/app workspace-mcp --transport streamable-http
Connect to Claude Desktop
The server supports two transport modes:
Stdio Mode (Default - Recommended for Claude Desktop)
Guided Setup (Recommended if not using DXT)
python install_claude.py
This script automatically:
- Prompts you for your Google OAuth credentials (Client ID and Secret).
- Creates the Claude Desktop config file in the correct location.
- Sets up all necessary environment variables.
- No manual file editing required!
After running the script, just restart Claude Desktop and you're ready to go.
Manual Claude Configuration (Alternative)
- Open Claude Desktop Settings → Developer → Edit Config
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
- Add the server configuration:
{
"mcpServers": {
"google_workspace": {
"command": "uvx",
"args": ["workspace-mcp"],
"env": {
"GOOGLE_OAUTH_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
"GOOGLE_OAUTH_CLIENT_SECRET": "your-client-secret",
"OAUTHLIB_INSECURE_TRANSPORT": "1"
}
}
}
}
Get Google OAuth Credentials (if you don't have them):
- Go to Google Cloud Console.
- Create a new project and enable APIs: Calendar, Drive, Gmail, Docs, Sheets, Slides, Forms, Tasks, Chat.
- Create OAuth 2.0 Client ID (Web application) with redirect URI:
http://localhost:8000/oauth2callback
.
Development Installation (For Contributors):
{
"mcpServers": {
"google_workspace": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/repo/google_workspace_mcp",
"main.py"
],
"env": {
"GOOGLE_OAUTH_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
"GOOGLE_OAUTH_CLIENT_SECRET": "your-client-secret",
"OAUTHLIB_INSECURE_TRANSPORT": "1"
}
}
}
}
HTTP Mode (For debugging or web interfaces)
If you need to use HTTP mode with Claude Desktop:
{
"mcpServers": {
"google_workspace": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:8000/mcp"]
}
}
}
⚠️ Important Note
Make sure to start the server with --transport streamable-http
when using HTTP mode.
First-Time Authentication
The server features transport-aware OAuth callback handling:
- Stdio Mode: Automatically starts a minimal HTTP server on port 8000 for OAuth callbacks.
- HTTP Mode: Uses the existing FastAPI server for OAuth callbacks.
- Same OAuth Flow: Both modes use
http://localhost:8000/oauth2callback
for consistency.
When calling a tool:
- Server returns authorization URL.
- Open URL in browser and authorize.
- Server handles OAuth callback automatically (on port 8000 in both modes).
- Retry the original request.
✨ Features
- 🔐 Advanced OAuth 2.0: Secure authentication with automatic token refresh, transport-aware callback handling, session management, and centralized scope management.
- 📅 Google Calendar: Full calendar management with event CRUD operations.
- 📁 Google Drive: File operations with native Microsoft Office format support (.docx, .xlsx).
- 📧 Gmail: Complete email management with search, send, and draft capabilities.
- 📄 Google Docs: Document operations including content extraction, creation, and comment management.
- 📊 Google Sheets: Comprehensive spreadsheet management with flexible cell operations and comment management.
- 🖼️ Google Slides: Presentation management with slide creation, updates, content manipulation, and comment management.
- 📝 Google Forms: Form creation, retrieval, publish settings, and response management.
- ✓ Google Tasks: Complete task and task list management with hierarchy, due dates, and status tracking.
- 💬 Google Chat: Space management and messaging capabilities.
- 🔄 All Transports: Stdio, Streamable HTTP & SSE, OpenAPI compatibility via
mcpo
.
- ⚡ High Performance: Service caching, thread-safe sessions, FastMCP integration.
- 🧩 Developer Friendly: Minimal boilerplate, automatic service injection, centralized configuration.
💻 Usage Examples
Basic Usage
from auth.service_decorator import require_google_service
@require_google_service("drive", "drive_read")
async def example_tool(service):
"""Example tool description"""
result = service.files().list().execute()
return result
Advanced Usage
from auth.service_decorator import require_multiple_services
@require_multiple_services(["drive", "calendar"])
async def advanced_example_tool(drive_service, calendar_service):
"""Advanced tool description"""
drive_result = drive_service.files().list().execute()
calendar_result = calendar_service.events().list().execute()
return drive_result, calendar_result
🧰 Available Tools
⚠️ Important Note
All tools support automatic authentication via @require_google_service()
decorators with 30-minute service caching.
Tool |
Description |
list_calendars |
List accessible calendars |
get_events |
Retrieve events with time range filtering |
get_event |
Fetch detailed information of a single event by ID |
create_event |
Create events (all-day or timed) with optional Drive file attachments |
modify_event |
Update existing events |
delete_event |
Remove events |
Tool |
Description |
search_drive_files |
Search files with query syntax |
get_drive_file_content |
Read file content (supports Office formats) |
list_drive_items |
List folder contents |
create_drive_file |
Create new files or fetch content from public URLs |
Tool |
Description |
search_gmail_messages |
Search with Gmail operators |
get_gmail_message_content |
Retrieve message content |
send_gmail_message |
Send emails |
draft_gmail_message |
Create drafts |
Tool |
Description |
search_docs |
Find documents by name |
get_doc_content |
Extract document text |
list_docs_in_folder |
List docs in folder |
create_doc |
Create new documents |
read_doc_comments |
Read all comments and replies |
create_doc_comment |
Create new comments |
reply_to_comment |
Reply to existing comments |
resolve_comment |
Resolve comments |
Tool |
Description |
list_spreadsheets |
List accessible spreadsheets |
get_spreadsheet_info |
Get spreadsheet metadata |
read_sheet_values |
Read cell ranges |
modify_sheet_values |
Write/update/clear cells |
create_spreadsheet |
Create new spreadsheets |
create_sheet |
Add sheets to existing files |
read_sheet_comments |
Read all comments and replies |
create_sheet_comment |
Create new comments |
reply_to_sheet_comment |
Reply to existing comments |
resolve_sheet_comment |
Resolve comments |
Tool |
Description |
create_presentation |
Create new presentations |
get_presentation |
Retrieve presentation details |
batch_update_presentation |
Apply multiple updates at once |
get_page |
Get specific slide information |
get_page_thumbnail |
Generate slide thumbnails |
read_presentation_comments |
Read all comments and replies |
create_presentation_comment |
Create new comments |
reply_to_presentation_comment |
Reply to existing comments |
resolve_presentation_comment |
Resolve comments |
Tool |
Description |
create_form |
Create new forms with title and description |
get_form |
Retrieve form details, questions, and URLs |
set_publish_settings |
Configure form template and authentication settings |
get_form_response |
Get individual form response details |
list_form_responses |
List all responses to a form with pagination |
Tool |
Description |
list_task_lists |
List all task lists with pagination support |
get_task_list |
Retrieve details of a specific task list |
create_task_list |
Create new task lists with custom titles |
update_task_list |
Modify existing task list titles |
delete_task_list |
Remove task lists and all contained tasks |
list_tasks |
List tasks in a specific list with filtering options |
get_task |
Retrieve detailed information about a specific task |
create_task |
Create new tasks with title, notes, due dates, and hierarchy |
update_task |
Modify task properties including title, notes, status, and due dates |
delete_task |
Remove tasks from task lists |
move_task |
Reposition tasks within lists or move between lists |
clear_completed_tasks |
Hide all completed tasks from a list |
Tool |
Description |
list_spaces |
List chat spaces/rooms |
get_messages |
Retrieve space messages |
send_message |
Send messages to spaces |
search_messages |
Search across chat history |
🛠️ Development
Project Structure
google_workspace_mcp/
├── auth/ # Authentication system with decorators
├── core/ # MCP server and utilities
├── g{service}/ # Service-specific tools
├── main.py # Server entry point
├── client_secret.json # OAuth credentials (not committed)
└── pyproject.toml # Dependencies
Adding New Tools
from auth.service_decorator import require_google_service
@require_google_service("drive", "drive_read")
async def your_new_tool(service, param1: str, param2: int = 10):
"""Tool description"""
result = service.files().list().execute()
return result
Architecture Highlights
- Service Caching: 30-minute TTL reduces authentication overhead.
- Scope Management: Centralized in
SCOPE_GROUPS
for easy maintenance.
- Error Handling: Native exceptions instead of manual error construction.
- Multi-Service Support:
@require_multiple_services()
for complex tools.
🔧 Technical Details
This production-ready MCP server integrates all major Google Workspace services with AI assistants. It is built with FastMCP for optimal performance, featuring advanced authentication handling, service caching, and streamlined development patterns. The server uses advanced OAuth 2.0 for secure authentication, with automatic token refresh, transport-aware callback handling, session management, and centralized scope management. Service caching and thread-safe sessions ensure high performance, while minimal boilerplate and automatic service injection make it developer-friendly.
🔒 Security
- Credentials: Never commit
client_secret.json
or .credentials/
directory.
- OAuth Callback: Uses
http://localhost:8000/oauth2callback
for development (requires OAUTHLIB_INSECURE_TRANSPORT=1
).
- Transport-Aware Callbacks: Stdio mode starts a minimal HTTP server only for OAuth, ensuring callbacks work in all modes.
- Production: Use HTTPS for callback URIs and configure accordingly.
- Network Exposure: Consider authentication when using
mcpo
over networks.
- Scope Minimization: Tools request only necessary permissions.
🌐 Integration with Open WebUI
To use this server as a tool provider within Open WebUI:
Instant Start (No Config Needed)
Just copy and paste the below, set your values and you're off!
GOOGLE_OAUTH_CLIENT_ID="your_client_id" GOOGLE_OAUTH_CLIENT_SECRET="your_client_secret" uvx mcpo --port 8000 --api-key "top-secret" -- uvx workspace-mcp
1. Create MCPO Configuration
Create a file named config.json
with the following structure to have mcpo
make the streamable HTTP endpoint available as an OpenAPI spec tool:
{
"mcpServers": {
"google_workspace": {
"type": "streamablehttp",
"url": "http://localhost:8000/mcp"
}
}
}
2. Start the MCPO Server
mcpo --port 8001 --config config.json --api-key "your-optional-secret-key"
This command starts the mcpo
proxy, serving your active (assuming port 8000) Google Workspace MCP on port 8001.
3. Configure Open WebUI
- Navigate to your Open WebUI settings.
- Go to "Connections" → "Tools".
- Click "Add Tool".
- Enter the Server URL:
http://localhost:8001/google_workspace
(matching the mcpo base URL and server name from config.json).
- If you used an
--api-key
with mcpo, enter it as the API Key.
- Save the configuration.
The Google Workspace tools should now be available when interacting with models in Open WebUI.
📄 License
MIT License - see LICENSE
file for details.