Google Workspace MCP Server
A Python-based MCP server that integrates Google Docs and Gmail, allowing appending text to documents and creating email drafts with terminal approval prompts.
README
Google Workspace MCP Server
This is a Python-based Model Context Protocol (MCP) style server integrating Google Docs and Gmail. It is built with FastAPI and runs on a local web server, exposing endpoints to append text to Google Documents and create email drafts in Gmail.
Before any action is executed, the server prompts the user in the terminal for approval: Approve? (y/n).
๐ Project Structure
google-mcp-server/
โโโ server.py # FastAPI server with tool endpoints & terminal approval logic
โโโ auth.py # Google OAuth 2.0 authentication flow
โโโ docs_tool.py # Google Docs tool (append content to document)
โโโ gmail_tool.py # Gmail tool (create email draft)
โโโ requirements.txt # Python package dependencies
โโโ README.md # Setup and usage instructions
โโโ credentials.json # (NOT committed) OAuth client credentials downloaded from Google Cloud
โโโ token.json # (NOT committed) Auto-generated user token after successful login
โ๏ธ Prerequisites
To run this server, you need to acquire a Google client configuration file:
- Go to the Google Cloud Console.
- Create a new project (or select an existing one).
- Enable the following APIs:
- Google Docs API
- Gmail API
- Set up the OAuth consent screen:
- Choose External user type (or Internal if using a Google Workspace organization account).
- Add test users (include your own Gmail address).
- Add the scopes:
https://www.googleapis.com/auth/documents(to append to documents)https://www.googleapis.com/auth/gmail.compose(to create drafts)
- Create Credentials:
- Click Create Credentials -> OAuth client ID.
- Select application type: Desktop app.
- Name it, click Create, and click Download JSON.
- Rename the downloaded file to
credentials.jsonand place it in the root of this project directory.
๐ Setup & Installation
-
Clone/Navigate to the workspace directory:
cd "c:\Users\amoln\Airtribe Projects\gmail_gdrive_mcp_server" -
Create and activate a virtual environment (optional but recommended):
python -m venv venv # On Windows (PowerShell): .\venv\Scripts\Activate.ps1 # On macOS/Linux: source venv/bin/activate -
Install the dependencies:
pip install -r requirements.txt
๐ Authentication
The authentication module auth.py automatically checks for a token.json file. If it doesn't exist, it opens a local browser server to execute the Google login flow.
You can trigger authentication manually before running the server:
python auth.py
This will open your browser. Grant the necessary permissions for Google Docs and Gmail, and the script will save token.json in the root folder. Future runs will read token.json directly and skip the browser login.
๐ Running the Server
Start the FastAPI server:
python server.py
The server will start listening on http://127.0.0.1:8005.
๐งช API Endpoints & Usage
1. Append to Google Doc
- Endpoint:
POST /append_to_doc - Request Body (JSON):
{ "doc_id": "YOUR_GOOGLE_DOCUMENT_ID", "content": "This text will be appended to the document.\n" } - Example request (
curl):curl -X POST "http://127.0.0.1:8005/append_to_doc" \ -H "Content-Type: application/json" \ -d "{\"doc_id\": \"1234567890abcdefghijklmnopqrstuvwxyz\", \"content\": \"Hello Google Docs!\n\"}"
2. Create Gmail Draft
- Endpoint:
POST /create_email_draft - Request Body (JSON):
{ "to": "recipient@example.com", "subject": "Hello from MCP Server", "body": "This is the body of the draft email." } - Example request (
curl):curl -X POST "http://127.0.0.1:8005/create_email_draft" \ -H "Content-Type: application/json" \ -d "{\"to\": \"recipient@example.com\", \"subject\": \"Test Subject\", \"body\": \"This is a test draft body.\"}"
๐ก๏ธ Terminal Approval Prompt
Whenever a request is sent to either of the endpoints, the server output will print the request details in the terminal and block:
========================================
ACTION NAME: append_to_doc
PAYLOAD:
doc_id: 1234567890abcdefghijklmnopqrstuvwxyz
content: Hello Google Docs!
========================================
Approve? (y/n):
- Type
yand press Enter: The action is sent to the Google APIs. The client receives a200 OKresponse. - Type
nand press Enter: The action is rejected. The API blocks execution and returns a403 Forbiddenresponse:{"detail":"Action rejected by user."}.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.