google-workspace-mcp-server
Enables appending content to Google Docs and creating Gmail drafts with interactive human-in-the-loop approval for safety.
README
Google Workspace MCP-Style Server (Python)
This project provides an HTTP-based Model Context Protocol (MCP) style server built in Python using FastAPI. It exposes tools to safely append reports to Google Docs and create drafts in Gmail, requiring interactive human-in-the-loop terminal confirmation before any modifications are executed.
š ļø Project Structure
google-mcp-server/
āāā server.py ā FastAPI app exposing endpoints with approval prompts
āāā auth.py ā Google API OAuth2 login & client token manager
āāā docs_tool.py ā Google Docs append operation logic
āāā gmail_tool.py ā Gmail draft creation logic
āāā requirements.txt ā Python package dependencies
āāā README.md ā Setup and execution instructions
āāā credentials.json ā (Not Committed) Downloaded OAuth credentials
āāā token.json ā (Not Committed) Authorized credentials token
āļø Prerequisites & Setup
1. Python Environment
Ensure Python 3.9+ is installed. Create and activate a virtual environment:
# Create venv
python3 -m venv venv
# Activate venv (macOS/Linux)
source venv/bin/activate
# Install dependencies
pip install -r requirements.txt
2. Configure Google Cloud Credentials
To authorize access to Google Docs and Gmail APIs:
- Go to the Google Cloud Console.
- Create a project (or select an existing one).
- Enable the Google Docs API and Gmail API under APIs & Services.
- Go to APIs & Services > Credentials.
- Click Create Credentials > OAuth client ID.
- Set the Application Type to Desktop app.
- Download the credentials JSON, rename it to
credentials.json, and place it in the root of thegoogle-mcp-serverdirectory.
š Running the Server
Start the FastAPI server:
python server.py
- First Run: A web page will automatically open in your browser prompting you to log into your Google Account and authorize access for Google Docs (modify) and Gmail (compose drafts) scopes. Once authenticated, a
token.jsonfile is written, and future runs execute silently.
The server runs locally at: http://localhost:8000
š API Endpoints (Tools)
1. Append to Google Doc
Appends a formatted text block to the end of a Doc.
- Endpoint:
POST /append_to_doc - Content-Type:
application/json - Request Body:
{ "doc_id": "your_google_doc_id_here", "content": "Verbatim text to append to the document body." }
2. Create Gmail Draft
Prepares a draft email in your mailbox.
- Endpoint:
POST /create_email_draft - Content-Type:
application/json - Request Body:
{ "to": "stakeholders@example.com", "subject": "Weekly review pulse teaser", "body": " Teaser summary and deep link to the Google Doc." }
š Security & Interactive Approvals
For safety, the server implements an interactive human-in-the-loop gatekeeper.
When a POST request is sent to /append_to_doc or /create_email_draft, the FastAPI server will:
- Print the pending action name and full payload details to the terminal console.
- Wait/block for keyboard confirmation:
Approve action? (y/n): - If
y: Executes the Google Workspace operation and returns a200 OKJSON response. - If
nor invalid: Aborts the operation and returns a403 Forbiddenerror response.
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.