gworkspace-mcp
An MCP server for automating Google Workspace applications including Sheets, Apps Script, Drive, Docs, and Gmail. It enables users to manipulate spreadsheets, edit scripts, manage files, and send emails directly from conversational AI interfaces.
README
gworkspace-mcp
Model Context Protocol server for Google Workspace automation: Google Sheets, Apps Script, Drive, Docs, Gmail, and triggers. Built with FastMCP.
Designed to be used from Claude Code (or any MCP-compatible client) so you can edit Apps Script projects, manipulate spreadsheets, send emails and manage Drive files directly from a conversation.
Features
- Apps Script (9 tools) — list, read, update, create, deploy and run Apps Script projects. Granular file edits so you don't have to rewrite entire scripts.
- Sheets (10 tools) — read/write ranges, batch updates, formatting, protection, formulas, dashboards.
- Drive (4 tools) — list, search, move and manage files.
- Docs (1 tool) — read/edit Google Docs.
- Gmail (3 tools) — compose and send email.
- Triggers (3 tools) — manage Apps Script time-based and event triggers.
- Connect (1 tool) — bind a local Apps Script project to a spreadsheet.
Requirements
- Python 3.10+
- A Google Cloud project with the following APIs enabled:
- Google Sheets API
- Google Drive API
- Apps Script API
- Google Docs API
- Gmail API
- Google Calendar API
- OAuth 2.0 Desktop credentials (
client_secret.json)
Installation
git clone https://github.com/LeooNic/gworkspace-mcp.git
cd gworkspace-mcp
pip install -e .
Or with uv:
uv pip install -e .
Google Cloud setup
- Go to console.cloud.google.com and create a project.
- Enable the APIs listed above under APIs & Services → Library.
- Go to APIs & Services → OAuth consent screen, configure it as External, and add your Google account as a test user.
- Go to APIs & Services → Credentials → Create Credentials → OAuth client ID, choose Desktop app, and download the JSON.
- Make the credentials available to the server in one of these ways:
- Place the JSON at
~/.secrets/gworkspace-mcp/client_secret.json, or - Set
GOOGLE_CLIENT_SECRET_PATH=/full/path/to/client_secret.json, or - Set
GOOGLE_OAUTH_CLIENT_IDandGOOGLE_OAUTH_CLIENT_SECRETas env vars.
- Place the JSON at
The first time a tool runs, a browser window will open for OAuth consent. The resulting token is stored at ~/.secrets/gworkspace-mcp/token.json and refreshed automatically.
Register with Claude Code
Add this to your Claude Code settings.json (or ~/.claude.json):
{
"mcpServers": {
"gworkspace": {
"command": "gworkspace-mcp"
}
}
}
If gworkspace-mcp is not on your PATH, use the absolute path to the executable created by pip install -e . (on Windows, typically C:\Users\<you>\AppData\Local\Programs\Python\Python3XX\Scripts\gworkspace-mcp.exe).
Alternative invocation without installing the entry point:
{
"mcpServers": {
"gworkspace": {
"command": "python",
"args": ["-m", "gworkspace_mcp.server"]
}
}
}
OAuth scopes
The server requests the following scopes:
spreadsheets,drive,documents,calendarscript.projects,script.deployments,script.processes,script.metricsgmail.send,gmail.composeuserinfo.email,userinfo.profile
Security notes
- Your
client_secret.jsonandtoken.jsonare personal — never commit them. The repo.gitignorealready excludes them. - Tokens live under
~/.secrets/gworkspace-mcp/. - The server runs locally; it does not expose any network endpoint.
License
MIT — see LICENSE.
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.