Google Workspace MCP Server

What is Google Workspace MCP Server about?

Provides a production‑ready backend that connects AI models and assistants to the full suite of Google Workspace APIs (Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Tasks, Chat and Custom Search). The server handles OAuth 2.1 multi‑user authentication, token refresh, and service caching, exposing each capability as MCP tools that can be called from any MCP‑compatible client.

How to use Google Workspace MCP Server?

1. Configure credentials – set GOOGLE_OAUTH_CLIENT_ID and GOOGLE_OAUTH_CLIENT_SECRET (environment variables, .env file, or client_secret.json).
2. Install – run uvx workspace-mcp (or uv run main.py for development).
3. Select tools – start with a tier (--tool-tier core|extended|complete) or specify individual services (--tools gmail drive calendar).
4. Launch – default stdio mode works with Claude Desktop; for HTTP clients add --transport streamable-http.
5. Authenticate – the server opens a Google consent URL; after granting access the flow completes automatically.

Key features

• Full coverage of Google Workspace APIs (Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Tasks, Chat, Custom Search).
• OAuth 2.1 multi‑user bearer‑token support with automatic token refresh.
• Three tool‑tiers (core, extended, complete) for granular API‑quota management.
• Service‑level caching (30‑minute TTL) reduces authentication overhead.
• One‑click Claude Desktop installer (.dxt) and seamless stdio integration.
• Docker‑ready images and configurable environment variables for cloud deployments.
• Optional CORS proxy architecture enabling browser‑based OAuth 2.1 flows.

Use cases

• AI assistants: let ChatGPT, Claude or custom LLMs read/write emails, schedule meetings, edit documents, and generate presentations via plain language.
• Automation scripts: trigger Google Workspace actions from CI/CD pipelines, bots, or serverless functions.
• Enterprise dashboards: expose calendar, drive, and task data through a unified API for internal tools.
• Education platforms: automate assignment distribution, grading spreadsheets, and class communication.
• Customer support: create tickets in Gmail, log interactions in Docs, and schedule follow‑ups automatically.

FAQ

Q: Do I need a Google Cloud project? A: Yes – create a project, enable the required APIs, and generate Desktop OAuth credentials.

Q: Can multiple users share the same server instance? A: Enable OAuth 2.1 (MCP_ENABLE_OAUTH21=true) and run the server in HTTP mode; each user authenticates with their own bearer token.

Q: Which Python version is required? A: Python 3.10 or newer.

Q: How do I limit the permissions each tool requests? A: Scopes are grouped per service in the code; only the scopes needed for the selected tier are requested.

Q: Is there a Docker image? A: Yes – build with docker build -t workspace-mcp . and run exposing port 8000.

Q: How does Claude Desktop integration work? A: Install the provided .dxt file; Claude Desktop launches the server automatically and injects the required environment variables.

Google Workspace MCP Server

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.

The most feature-complete Google Workspace MCP server, now with Remote OAuth2.1 multi-user support and 1-click Claude installation.

Support for all free Google accounts (Gmail, Docs, Drive etc) & Google Workspace plans (Starter, Standard, Plus, Enterprise, Non Profit) with expanded app options like Chat & Spaces. Interested in a private cloud instance? That can be arranged.

---

See it in action:

---

A quick plug for AI-Enhanced Docs

This README was written with AI assistance, and here's why that matters

As a solo dev building open source tools, 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 8/16/25.

Overview

A production-ready MCP server that integrates all major Google Workspace services with AI assistants. It supports both single-user operation and multi-user authentication via OAuth 2.1, making it a powerful backend for custom applications. Built with FastMCP for optimal performance, featuring advanced authentication handling, service caching, and streamlined development patterns.

Simplified Setup: Now uses Google Desktop OAuth clients - no redirect URIs or port configuration needed!

Features

@ Gmail • ≡ Drive • ⧖ Calendar ≡ Docs

• Complete Gmail management, end to end coverage
• Full calendar management with advanced features
• File operations with Office format support
• Document creation, editing & comments
• Deep, exhaustive support for fine grained editing

---

≡ Forms • @ Chat • ≡ Sheets • ≡ Slides

• Form creation, publish settings & response management
• Space management & messaging capabilities
• Spreadsheet operations with flexible cell management
• Presentation creation, updates & content manipulation

⊠ Authentication & Security

• Advanced OAuth 2.0 & OAuth 2.1 support
• Automatic token refresh & session management
• Transport-aware callback handling
• Multi-user bearer token authentication
• Innovative CORS proxy architecture

---

✓ Tasks • ◆ Custom Search • ↻ Transport Support

• Full support for all MCP Transports
• OpenAPI compatibility via mcpo
• Task & task list management with hierarchy
• Programmable Search Engine (PSE) integration

---

▶ Quick Start

⊠ Credentials

export GOOGLE_OAUTH_CLIENT_ID="..."
export GOOGLE_OAUTH_CLIENT_SECRET="..."

Full setup →

▶ Launch Commands

uvx workspace-mcp --tool-tier core
uv run main.py --tools gmail drive

More options →

★ Tool Tiers

• ● core - Essential tools
• ◐ extended - Core + extras
• ○ complete - Everything Details →

1. One-Click Claude Desktop Install (Recommended)

1. Download: Grab the latest google_workspace_mcp.dxt from the “Releases” page
2. Install: Double-click the file – Claude Desktop opens and prompts you to Install
3. Configure: In Claude Desktop → Settings → Extensions → Google Workspace MCP, paste your Google OAuth credentials
4. Use it: Start a new Claude chat and call any Google Workspace tool

Why DXT?

Desktop Extensions (.dxt) bundle the server, dependencies, and manifest so users go from download → working MCP in one click – no terminal, no JSON editing, no version conflicts.

Required Configuration

Required

Variable	Purpose
GOOGLE_OAUTH_CLIENT_ID	OAuth client ID from Google Cloud
GOOGLE_OAUTH_CLIENT_SECRET	OAuth client secret
OAUTHLIB_INSECURE_TRANSPORT=1	Development only (allows http:// redirect)

Optional

Variable	Purpose
USER_GOOGLE_EMAIL	Default email for single-user auth
GOOGLE_PSE_API_KEY	API key for Custom Search
GOOGLE_PSE_ENGINE_ID	Search Engine ID for Custom Search
MCP_ENABLE_OAUTH21	Set to true for OAuth 2.1 support

Claude Desktop stores these securely in the OS keychain; set them once in the extension pane.

---

---

Prerequisites

• Python 3.10+
• uvx (for instant installation) or uv (for development)
• Google Cloud Project with OAuth 2.0 credentials

Configuration

1. Create Project

console.cloud.google.com

→ Create new project
→ Note project name

Open Console →

2. OAuth Credentials

APIs & Services → Credentials
→ Create Credentials
→ OAuth Client ID
→ Desktop Application

Download & save credentials

3. Enable APIs

APIs & Services → Library

Search & enable:
Calendar, Drive, Gmail,
Docs, Sheets, Slides,
Forms, Tasks, Chat, Search

See quick links below

Complete Setup Process:

1. Create OAuth 2.0 Credentials - Visit Google Cloud Console

   • Create a new project (or use existing)
   • Navigate to APIs & Services → Credentials
   • Click Create Credentials → OAuth Client ID
   • Choose Desktop Application as the application type (no redirect URIs needed!)
   • Download credentials and note the Client ID and Client Secret

2. Enable Required APIs - In APIs & Services → Library

   • Search for and enable each required API
   • Or use the quick links below for one-click enabling

3. Configure Environment - Set your credentials:

   export GOOGLE_OAUTH_CLIENT_ID="your-client-id"
   export GOOGLE_OAUTH_CLIENT_SECRET="your-secret"
   

≡ Full Documentation →

• Enable Google Calendar API
• Enable Google Drive API
• Enable Gmail API
• Enable Google Docs API
• Enable Google Sheets API
• Enable Google Slides API
• Enable Google Forms API
• Enable Google Tasks API
• Enable Google Chat API
• Enable Google Custom Search API

1.1. Credentials: See Credential Configuration for detailed setup options

2. Environment Configuration:

◆ Development Mode

export OAUTHLIB_INSECURE_TRANSPORT=1

Allows HTTP redirect URIs

@ Default User

export USER_GOOGLE_EMAIL=\
  your.email@gmail.com

Single-user authentication

◆ Custom Search

export GOOGLE_PSE_API_KEY=xxx
export GOOGLE_PSE_ENGINE_ID=yyy

Optional: Search API setup

3. Server Configuration:

◆ Base Configuration

export WORKSPACE_MCP_BASE_URI=
  http://localhost
export WORKSPACE_MCP_PORT=8000

Server URL & port settings

↻ Proxy Support

export MCP_ENABLE_OAUTH21=
  true

Leverage multi-user OAuth2.1 clients

@ Default Email

export USER_GOOGLE_EMAIL=\
  your.email@gmail.com

Skip email in auth flows in single user mode

Variable	Description	Default
WORKSPACE_MCP_BASE_URI	Base server URI (no port)	http://localhost
WORKSPACE_MCP_PORT	Server listening port	8000
GOOGLE_OAUTH_REDIRECT_URI	Override OAuth callback URL	Auto-constructed
USER_GOOGLE_EMAIL	Default auth email	None

Google Custom Search Setup

1. Create Search Engine

programmablesearchengine.google.com
/controlpanel/create

→ Configure sites or entire web
→ Note your Engine ID (cx)

Open Control Panel →

2. Get API Key

developers.google.com
/custom-search/v1/overview

→ Create/select project
→ Enable Custom Search API
→ Create credentials (API Key)

Get API Key →

3. Set Variables

export GOOGLE_PSE_API_KEY=\
  "your-api-key"
export GOOGLE_PSE_ENGINE_ID=\
  "your-engine-id"

Configure in environment

Complete Setup Process:

1. Create Search Engine - Visit the Control Panel

   • Choose "Search the entire web" or specify sites
   • Copy the Search Engine ID (looks like: 017643444788157684527:6ivsjbpxpqw)

2. Enable API & Get Key - Visit Google Developers Console

   • Enable "Custom Search API" in your project
   • Create credentials → API Key
   • Restrict key to Custom Search API (recommended)

3. Configure Environment - Add to your shell or .env:

   export GOOGLE_PSE_API_KEY="AIzaSy..."
   export GOOGLE_PSE_ENGINE_ID="01764344478..."
   

≡ Full Documentation →

Start the Server

▶ Quick Start

uv run main.py

Default stdio mode

◆ HTTP Mode

uv run main.py \
  --transport streamable-http

Web interfaces & debugging

@ Single User

uv run main.py \
  --single-user

Simplified authentication

▶ Selective Tool Loading

# Load specific services only
uv run main.py --tools gmail drive calendar
uv run main.py --tools sheets docs

# Combine with other flags
uv run main.py --single-user --tools gmail

★ Tool Tiers

uv run main.py --tool-tier core      # ● Essential tools only
uv run main.py --tool-tier extended  # ◐ Core + additional
uv run main.py --tool-tier complete  # ○ All available tools

◆ Docker Deployment

docker build -t workspace-mcp .
docker run -p 8000:8000 -v $(pwd):/app \
  workspace-mcp --transport streamable-http

# With tool selection via environment variables
docker run -e TOOL_TIER=core workspace-mcp
docker run -e TOOLS="gmail drive calendar" workspace-mcp

Available Services: gmail • drive • calendar • docs • sheets • forms • tasks • chat • search

Tool Tiers

The server organizes tools into three progressive tiers for simplified deployment. Choose a tier that matches your usage needs and API quota requirements.

Available Tiers

● Core (--tool-tier core) Essential tools for everyday tasks. Perfect for light usage with minimal API quotas. Includes search, read, create, and basic modify operations across all services.

● Extended (--tool-tier extended) Core functionality plus management tools. Adds labels, folders, batch operations, and advanced search. Ideal for regular usage with moderate API needs.

● Complete (--tool-tier complete) Full API access including comments, headers/footers, publishing settings, and administrative functions. For power users needing maximum functionality.

Important Notes

▶ Start with core and upgrade as needed ▶ Tiers are cumulative – each includes all previous ▶ Mix and match with --tools for specific services ▶ Configuration in core/tool_tiers.yaml ▶ Authentication included in all tiers

Usage Examples

# Basic tier selection
uv run main.py --tool-tier core                            # Start with essential tools only
uv run main.py --tool-tier extended                        # Expand to include management features
uv run main.py --tool-tier complete                        # Enable all available functionality

# Selective service loading with tiers
uv run main.py --tools gmail drive --tool-tier core        # Core tools for specific services
uv run main.py --tools gmail --tool-tier extended          # Extended Gmail functionality only
uv run main.py --tools docs sheets --tool-tier complete    # Full access to Docs and Sheets

📋 Credential Configuration

🚀 Environment Variables

export GOOGLE_OAUTH_CLIENT_ID=\
  "your-client-id"
export GOOGLE_OAUTH_CLIENT_SECRET=\
  "your-secret"

Best for production

📁 File-based

# Download & place in project root
client_secret.json

# Or specify custom path
export GOOGLE_CLIENT_SECRET_PATH=\
  /path/to/secret.json

Traditional method

⚡ .env File

cp .env.oauth21 .env
# Edit .env with credentials

Best for development

Loading Priority

1. Environment variables (export VAR=value)
2. .env file in project root
3. client_secret.json via GOOGLE_CLIENT_SECRET_PATH
4. Default client_secret.json in project root

Why Environment Variables?

• ✅ Docker/K8s ready - Native container support
• ✅ Cloud platforms - Heroku, Railway, Vercel
• ✅ CI/CD pipelines - GitHub Actions, Jenkins
• ✅ No secrets in git - Keep credentials secure
• ✅ Easy rotation - Update without code changes

---

🧰 Available Tools

Note: All tools support automatic authentication via @require_google_service() decorators with 30-minute service caching.

📅 Google Calendar calendar_tools.py

Tool	Tier	Description
list_calendars	Core	List accessible calendars
get_events	Core	Retrieve events with time range filtering
create_event	Core	Create events with attachments & reminders
modify_event	Core	Update existing events
delete_event	Extended	Remove events

📁 Google Drive drive_tools.py

Tool	Tier	Description
search_drive_files	Core	Search files with query syntax
get_drive_file_content	Core	Read file content (Office formats)
list_drive_items	Extended	List folder contents
create_drive_file	Core	Create files or fetch from URLs

📧 Gmail gmail_tools.py

Tool	Tier	Description
search_gmail_messages	Core	Search with Gmail operators
get_gmail_message_content	Core	Retrieve message content
get_gmail_messages_content_batch	Core	Batch retrieve message content
send_gmail_message	Core	Send emails
get_gmail_thread_content	Extended	Get full thread content
modify_gmail_message_labels	Extended	Modify message labels
list_gmail_labels	Extended	List available labels
manage_gmail_label	Extended	Create/update/delete labels
draft_gmail_message	Extended	Create drafts
get_gmail_threads_content_batch	Complete	Batch retrieve thread content
batch_modify_gmail_message_labels	Complete	Batch modify labels
start_google_auth	Complete	Initialize authentication

📝 Google Docs docs_tools.py

Tool	Tier	Description
get_doc_content	Core	Extract document text
create_doc	Core	Create new documents
modify_doc_text	Core	Modify document text
search_docs	Extended	Find documents by name
find_and_replace_doc	Extended	Find and replace text
list_docs_in_folder	Extended	List docs in folder
insert_doc_elements	Extended	Add tables, lists, page breaks
insert_doc_image	Complete	Insert images from Drive/URLs
update_doc_headers_footers	Complete	Modify headers and footers
batch_update_doc	Complete	Execute multiple operations
inspect_doc_structure	Complete	Analyze document structure
create_table_with_data	Complete	Create data tables
debug_table_structure	Complete	Debug table issues
*_document_comments	Complete	Read, Reply, Create, Resolve

📊 Google Sheets sheets_tools.py

Tool	Tier	Description
read_sheet_values	Core	Read cell ranges
modify_sheet_values	Core	Write/update/clear cells
create_spreadsheet	Core	Create new spreadsheets
list_spreadsheets	Extended	List accessible spreadsheets
get_spreadsheet_info	Extended	Get spreadsheet metadata
create_sheet	Complete	Add sheets to existing files
*_sheet_comment	Complete	Read/create/reply/resolve comments

🖼️ Google Slides slides_tools.py

Tool	Tier	Description
create_presentation	Core	Create new presentations
get_presentation	Core	Retrieve presentation details
batch_update_presentation	Extended	Apply multiple updates
get_page	Extended	Get specific slide information
get_page_thumbnail	Extended	Generate slide thumbnails
*_presentation_comment	Complete	Read/create/reply/resolve comments

📝 Google Forms forms_tools.py

Tool	Tier	Description
create_form	Core	Create new forms
get_form	Core	Retrieve form details & URLs
set_publish_settings	Complete	Configure form settings
get_form_response	Complete	Get individual responses
list_form_responses	Extended	List all responses with pagination

✓ Google Tasks tasks_tools.py

Tool	Tier	Description
list_tasks	Core	List tasks with filtering
get_task	Core	Retrieve task details
create_task	Core	Create tasks with hierarchy
update_task	Core	Modify task properties
delete_task	Extended	Remove tasks
move_task	Complete	Reposition tasks
clear_completed_tasks	Complete	Hide completed tasks
*_task_list	Complete	List/get/create/update/delete task lists

💬 Google Chat chat_tools.py

Tool	Tier	Description
list_spaces	Extended	List chat spaces/rooms
get_messages	Core	Retrieve space messages
send_message	Core	Send messages to spaces
search_messages	Core	Search across chat history

🔍 Google Custom Search search_tools.py

Tool	Tier	Description
search_custom	Core	Perform web searches
get_search_engine_info	Complete	Retrieve search engine metadata
search_custom_siterestrict	Extended	Search within specific domains

Tool Tier Legend:

• • Core: Essential tools for basic functionality • Minimal API usage • Getting started
• • Extended: Core tools + additional features • Regular usage • Expanded capabilities
• • Complete: All available tools including advanced features • Power users • Full API access

---

Connect to Claude Desktop

The server supports two transport modes:

Stdio Mode (Default - Recommended for Claude Desktop)

In general, you should use the one-click DXT installer package for Claude Desktop. If you are unable to for some reason, you can configure it manually via claude_desktop_config.json

Manual Claude Configuration (Alternative)

1. Open Claude Desktop Settings → Developer → Edit Config

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json

2. Add the server configuration:

{
  "mcpServers": {
    "google_workspace": {
      "command": "uvx",
      "args": ["workspace-mcp"],
      "env": {
        "GOOGLE_OAUTH_CLIENT_ID": "your-client-id",
        "GOOGLE_OAUTH_CLIENT_SECRET": "your-secret",
        "OAUTHLIB_INSECURE_TRANSPORT": "1"
      }
    }
  }
}

2. Advanced / Cross-Platform Installation

If you’re developing, deploying to servers, or using another MCP-capable client, keep reading.

Instant CLI (uvx)

# Requires Python 3.10+ and uvx
# First, set credentials (see Credential Configuration above)
uvx workspace-mcp --tool-tier core  # or --tools gmail drive calendar

Note: Configure OAuth credentials before running. Supports environment variables, .env file, or client_secret.json.

OAuth 2.1 Support (Multi-User Bearer Token Authentication)

The server includes OAuth 2.1 support for bearer token authentication, enabling multi-user session management. OAuth 2.1 automatically reuses your existing GOOGLE_OAUTH_CLIENT_ID and GOOGLE_OAUTH_CLIENT_SECRET credentials - no additional configuration needed!

When to use OAuth 2.1:

• Multiple users accessing the same MCP server instance
• Need for bearer token authentication instead of passing user emails
• Building web applications or APIs on top of the MCP server
• Production environments requiring secure session management
• Browser-based clients requiring CORS support

Enabling OAuth 2.1: To enable OAuth 2.1, set the MCP_ENABLE_OAUTH21 environment variable to true.

# OAuth 2.1 requires HTTP transport mode
export MCP_ENABLE_OAUTH21=true
uv run main.py --transport streamable-http

If MCP_ENABLE_OAUTH21 is not set to true, the server will use legacy authentication, which is suitable for clients that do not support OAuth 2.1.

This implementation solves two critical challenges when using Google OAuth in browser environments:

1. Dynamic Client Registration: Google doesn't support OAuth 2.1 dynamic client registration. Our server provides a clever proxy that accepts any client registration request and returns the pre-configured Google OAuth credentials, allowing standards-compliant clients to work seamlessly.

2. CORS Issues: Google's OAuth endpoints don't include CORS headers, blocking browser-based clients. We implement intelligent proxy endpoints that:

• Proxy authorization server discovery requests through /auth/discovery/authorization-server/{server}
• Proxy token exchange requests through /oauth2/token
• Add proper CORS headers to all responses
• Maintain security by only proxying to known Google OAuth endpoints

This architecture enables any OAuth 2.1 compliant client to authenticate users through Google, even from browser environments, without requiring changes to the client implementation.

MCP Inspector: No additional configuration needed with desktop OAuth client.

Claude Code Inspector: No additional configuration needed with desktop OAuth client.

VS Code MCP Client Support

{
    "servers": {
        "google-workspace": {
            "url": "http://localhost:8000/mcp/",
            "type": "http"
        }
    }
}

Reverse Proxy Setup

If you're running the MCP server behind a reverse proxy (nginx, Apache, Cloudflare, etc.), you'll need to configure GOOGLE_OAUTH_REDIRECT_URI to match your external URL:

Problem: When behind a reverse proxy, the server constructs redirect URIs using internal ports (e.g., http://localhost:8000/oauth2callback) but Google expects the external URL (e.g., https://your-domain.com/oauth2callback).

You also have options for: | OAUTH_CUSTOM_REDIRECT_URIS (optional) | Comma-separated list of additional redirect URIs | | OAUTH_ALLOWED_ORIGINS (optional) | Comma-separated list of additional CORS origins |

Solution: Set GOOGLE_OAUTH_REDIRECT_URI to your external URL:

# External URL without port (nginx/Apache handling HTTPS)
export GOOGLE_OAUTH_REDIRECT_URI="https://your-domain.com/oauth2callback"

# Or with custom port if needed
export GOOGLE_OAUTH_REDIRECT_URI="https://your-domain.com:8443/oauth2callback"

Important:

• The redirect URI must exactly match what's configured in your Google Cloud Console
• The server will use this value for all OAuth flows instead of constructing it from WORKSPACE_MCP_BASE_URI and WORKSPACE_MCP_PORT
• Your reverse proxy must forward /oauth2callback requests to the MCP server

# Configure credentials first (see Credential Configuration section)

# Start with specific tools only
uvx workspace-mcp --tools gmail drive calendar tasks

# Start with tool tiers (recommended for most users)
uvx workspace-mcp --tool-tier core      # Essential tools
uvx workspace-mcp --tool-tier extended  # Core + additional features
uvx workspace-mcp --tool-tier complete  # All tools

# Start in HTTP mode for debugging
uvx workspace-mcp --transport streamable-http

Requires Python 3.10+ 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

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",
        "GOOGLE_OAUTH_CLIENT_SECRET": "your-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"]
    }
  }
}

Note: Make sure to start the server with --transport streamable-http when using HTTP mode.

First-Time Authentication

The server uses Google Desktop OAuth for simplified authentication:

• No redirect URIs needed: Desktop OAuth clients handle authentication without complex callback URLs
• Automatic flow: The server manages the entire OAuth process transparently
• Transport-agnostic: Works seamlessly in both stdio and HTTP modes

When calling a tool:

1. Server returns authorization URL
2. Open URL in browser and authorize
3. Google provides an authorization code
4. Paste the code when prompted (or it's handled automatically)
5. Server completes authentication and retries your request

---

◆ 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")  # Service + scope group
async def your_new_tool(service, param1: str, param2: int = 10):
    """Tool description"""
    # service is automatically injected and cached
    result = service.files().list().execute()
    return result  # Return native Python objects

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

Credential Store System

The server includes an abstract credential store API and a default backend for managing Google OAuth credentials with support for multiple storage backends:

Features:

• Abstract Interface: CredentialStore base class defines standard operations (get, store, delete, list users)
• Local File Storage: LocalDirectoryCredentialStore implementation stores credentials as JSON files
• Configurable Storage: Environment variable GOOGLE_MCP_CREDENTIALS_DIR sets storage location
• Multi-User Support: Store and manage credentials for multiple Google accounts
• Automatic Directory Creation: Storage directory is created automatically if it doesn't exist

Configuration:

# Optional: Set custom credentials directory
export GOOGLE_MCP_CREDENTIALS_DIR="/path/to/credentials"

# Default locations (if GOOGLE_MCP_CREDENTIALS_DIR not set):
# - ~/.google_workspace_mcp/credentials (if home directory accessible)
# - ./.credentials (fallback)

Usage Example:

from auth.credential_store import get_credential_store

# Get the global credential store instance
store = get_credential_store()

# Store credentials for a user
store.store_credential("user@example.com", credentials)

# Retrieve credentials
creds = store.get_credential("user@example.com")

# List all users with stored credentials
users = store.list_users()

The credential store automatically handles credential serialization, expiry parsing, and provides error handling for storage operations.

---

⊠ Security

• Credentials: Never commit .env, client_secret.json or the .credentials/ directory to source control!
• 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 & OAuth 2.1 and configure accordingly
• Network Exposure: Consider authentication when using mcpo over networks
• Scope Minimization: Tools request only necessary permissions

---

◆ Integration with Open WebUI

▶ Instant Start (No Config)

# Set credentials & launch in one command
GOOGLE_OAUTH_CLIENT_ID="your_id" \
GOOGLE_OAUTH_CLIENT_SECRET="your_secret" \
uvx mcpo --port 8000 --api-key "secret" \
-- uvx workspace-mcp

◆ Manual Configuration

1. Create config.json:

{
  "mcpServers": {
    "google_workspace": {
      "type": "streamablehttp",
      "url": "http://localhost:8000/mcp"
    }
  }
}

2. Start MCPO:

mcpo --port 8001 --config config.json

≡ Configure Open WebUI

1. Navigate to Settings → Connections → Tools
2. Click Add Tool and enter:
   • Server URL: http://localhost:8001/google_workspace
   • API Key: Your mcpo --api-key (if set)
3. Save - Google Workspace tools are now available!

---

≡ License

MIT License - see LICENSE file for details.

---

Validations: