Google Workspace MCP Server
Provides tools for searching, reading, and sending emails via Gmail API.
Provides tools for reading and creating Google Docs via Google Docs API.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Google Workspace MCP Server
This project is an MCP (Model Context Protocol) server that provides tools to interact with Gmail and Google Docs.
Prerequisites
Python 3.10+
Google Cloud Project: You need to create a project in the Google Cloud Console and enable the Gmail and Google Docs APIs.
Setting up Google Cloud Credentials
Go to the Google Cloud Console.
Create a new project.
Go to APIs & Services > Library.
Search for and enable Gmail API and Google Docs API.
Go to APIs & Services > OAuth consent screen.
Choose External (or Internal if you have a Google Workspace org).
Fill in the required app information.
Add the following scopes:
https://www.googleapis.com/auth/gmail.modifyhttps://www.googleapis.com/auth/documents
Add your Google email address as a Test user.
Go to APIs & Services > Credentials.
Click Create Credentials > OAuth client ID.
Choose Desktop app as the application type.
Click Create and then Download JSON.
Rename the downloaded file to
credentials.jsonand place it in the root directory of this project.
Related MCP server: Moist
Installation
It is recommended to use a virtual environment.
python -m venv venv
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate
pip install -r requirements.txtRunning the Server
To start the MCP server, use the mcp CLI tool (installed via dependencies):
mcp dev main.pyThe first time you run this, a browser window will open asking you to log in with your Google account and grant permissions to the app. After granting permissions, a token.json file will be created locally to store your access and refresh tokens.
Available Tools
The following tools will be exposed to your LLM:
search_emails(query, max_results): Search for emails matching a Gmail query.read_email(message_id): Read the content of a specific email.send_email(to, subject, body): Send an email.read_document(document_id): Read the text content of a Google Doc.create_document(title, content): Create a new Google Doc with optional initial content.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
Permissioned access to Gmail, Drive and Calendar via the user's own Google account
A MCP server for Gmail that lets you search, read, and draft emails and replies.
Google Docs MCP Pack — read, create, and edit Google Docs via OAuth. Reuses the google_sheets…
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Gmail through the MCP protocol, supporting sending, reading, searching, replying, forwarding, managing drafts and labels, and saving attachments.7 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables Gmail operations such as reading, sending, searching, and managing emails, threads, labels, and drafts via MCP tools.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables sending emails and managing drafts in Gmail, and appending content to Google Docs, via MCP-compatible clients.1,276 npmMIT
- FlicenseNot gradedqualityCmaintenanceEnables MCP-compatible AI agents to draft and send Gmail emails and append content to Google Docs without needing to understand Google's APIs.-