mcp-google-suite
MCP Google Workspace Server
Documentation
MCP Google Workspace Server
A Model Context Protocol (MCP) server enabling AI agents to interact with Google Workspace (Drive, Docs, and Sheets) services.
๐ Features
- Google Drive: Search files, create folders
- Google Docs: Create, read, update documents
- Google Sheets: Create spreadsheets, read/write cell values
- Multiple transport modes: stdio (default), SSE, WebSocket
- MCP-compatible client support (Cursor, etc.)
๐ Installation
Using uv (recommended)
uvx mcp-google-suiteUsing pip
pip install mcp-google-suiteDevelopment setup
# Clone and install
git clone git@github.com:adexltd/mcp-google-suite.git && cd mcp-google-suite
uv venv && source .venv/bin/activate # or .venv\Scripts\activate on Windows
uv pip install -e .๐ง Configuration
Configure for MCP Clients
Add to your client settings (e.g. Cursor, Claude):
Using uvx (recommended):
{
"mcpServers": {
"mcp-google-suite": {
"command": "uvx",
"args": ["mcp-google-suite"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "~/.google/server-creds.json",
"GOOGLE_OAUTH_CREDENTIALS": "~/.google/oauth.keys.json"
}
}
}
}Using pip installation:
{
"mcpServers": {
"mcp-google-suite": {
"command": "python",
"args": ["-m", "mcp_google_suite"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "~/.google/server-creds.json",
"GOOGLE_OAUTH_CREDENTIALS": "~/.google/oauth.keys.json"
}
}
}
}Google OAuth Setup
1. Visit Google Cloud Console
2. Enable Drive, Docs, and Sheets APIs
3. Create OAuth 2.0 credentials
4. Save as `~/.google/oauth.keys.json`
5. Run `mcp-google auth` to authenticate
Available Tools
Drive Operations
- `drive_search_files`: Search files in Google Drive
- `query` (string, required): Search query
- `page_size` (integer, optional): Number of results to return
- `drive_create_folder`: Create a new folder
- `name` (string, required): Folder name
- `parent_id` (string, optional): Parent folder ID
Docs Operations
- `docs_create`: Create a new document
- `title` (string, required): Document title
- `content` (string, optional): Initial content
- `docs_get_content`: Get document content
- `document_id` (string, required): Document ID
- `docs_update_content`: Update document content
- `document_id` (string, required): Document ID
- `content` (string, required): New content
Sheets Operations
- `sheets_create`: Create a new spreadsheet
- `title` (string, required): Spreadsheet title
- `sheets` (array, optional): Sheet names
- `sheets_get_values`: Get cell values
- `spreadsheet_id` (string, required): Spreadsheet ID
- `range` (string, required): A1 notation range
- `sheets_update_values`: Update cell values
- `spreadsheet_id` (string, required): Spreadsheet ID
- `range` (string, required): A1 notation range
- `values` (array, required): 2D array of values
๐ ๏ธ Development
# Install dev dependencies
uv pip install -e ".[dev]"
# Setup pre-commit hooks
pre-commit install
# Run tests
pytest
# Format code
black . && ruff check --fix .๐ Debugging
Use the MCP Inspector for interactive testing:
# Using uvx
npx @modelcontextprotocol/inspector uvx mcp-google
# For development
cd path/to/mcp-google-suite
npx @modelcontextprotocol/inspector uv run mcp-google๐ Resources
๐ค Contributing
Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.
๐ Security
See SECURITY.md for reporting vulnerabilities and best practices.
๐ License
MIT License - See LICENSE file for details.
Frequently asked questions
What is mcp-google-suite?
mcp-google-suite is MCP Google Workspace Server
How do I install mcp-google-suite?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-google-suite open source?
Yes โ it is hosted on GitHub at https://github.com/adexltd/mcp-google-suite and has 3 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP