Google Workspace MCP Server
Allows sending emails (plain-text or HTML) with support for multiple recipients, CC, and BCC.
Allows appending text to existing Google Documents.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Google Workspace MCP Serversend an email to alice@example.com with subject 'Meeting reminder' and body 'Don't forget the 3pm meeting.'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Google Workspace MCP Server
This is a Model Context Protocol (MCP) server that provides AI agents with tools to interact with Google Workspace services (Gmail and Google Docs).
Available Tools
send_email: Send an email via Gmail (supports multiple recipients, CC, BCC, plain-text and HTML).append_google_doc: Append text to an existing Google Document.
Related MCP server: Gmail MCP Server
Setup Instructions
1. Configure Environment Variables
Rename .env.example to .env and fill in your Google Cloud credentials.
GOOGLE_CLIENT_ID=your_client_id
GOOGLE_CLIENT_SECRET=your_client_secret
GOOGLE_REDIRECT_URI=http://localhost:3000/oauth2callback
PORT=3000
TOKEN_PATH=tokens.json2. Generate Authentication Tokens
Before starting the MCP server, you must grant it access to your Google account. Run the authentication script:
npm run authClick the link printed in your terminal.
Sign in with your Google account.
Grant the required permissions for Gmail and Google Docs.
The script will automatically generate
tokens.jsonin your workspace.
3. Build the Server
Compile the TypeScript code:
npm run build4. Connect to an MCP Client (e.g., Claude Desktop)
To use this server with Claude Desktop or another MCP client, configure the client to run the compiled index.js file. Add the following to your MCP client configuration file (e.g. claude_desktop_config.json):
{
"mcpServers": {
"google-workspace": {
"command": "node",
"args": ["/absolute/path/to/mcp-server/build/index.js"],
"env": {
"GOOGLE_CLIENT_ID": "your_client_id",
"GOOGLE_CLIENT_SECRET": "your_client_secret",
"GOOGLE_REDIRECT_URI": "http://localhost:3000/oauth2callback",
"TOKEN_PATH": "/absolute/path/to/mcp-server/tokens.json"
}
}
}
}Note: Ensure the TOKEN_PATH environment variable in the client config points to the absolute path of your generated tokens.json file.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rparvathysuresh/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server