Google MCP Server
A Python FastAPI server that exposes Google Docs and Gmail tools with terminal-based approval before each action. Allows appending to Google Docs and creating Gmail drafts.
README
Google MCP Server
A Python FastAPI server that exposes Google Docs and Gmail tools with terminal-based approval before each action.
Features
- POST /append_to_doc — Append text to a Google Doc
- POST /create_email_draft — Create a Gmail draft
- Approval gate — Every action prints its name and payload, then waits for
yin the terminal before executing
Project Structure
google-mcp-server/
├── server.py # FastAPI app with tool endpoints
├── auth.py # Google OAuth authentication
├── docs_tool.py # Google Docs tool (append content)
├── gmail_tool.py # Gmail tool (create draft)
├── requirements.txt # Dependencies
├── credentials.json # OAuth client secrets (not committed)
└── token.json # Saved OAuth token (not committed)
Prerequisites
- A Google Cloud project
- Google Docs API and Gmail API enabled
- OAuth 2.0 Desktop app credentials downloaded as
credentials.json
Google Cloud setup
- Go to Google Cloud Console → APIs & Services → Library.
- Enable Google Docs API and Gmail API.
- Go to APIs & Services → Credentials → Create Credentials → OAuth client ID.
- Application type: Desktop app.
- Download the JSON file and save it as
credentials.jsonin this directory. - Under OAuth consent screen, add your Google account as a test user (if the app is in testing mode).
Installation
cd google-mcp-server
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
Place credentials.json in the project root before starting the server.
First-time authentication
On the first API call that needs Google access, a browser window opens for OAuth login. After you approve, a token.json file is created. Subsequent runs reuse that token (refreshing it automatically when expired).
Run the server
python server.py
Or with uvicorn directly:
uvicorn server:app --host 127.0.0.1 --port 8000 --reload
The server runs at http://127.0.0.1:8000. Interactive API docs: http://127.0.0.1:8000/docs.
Important: Run the server in a terminal where you can type
yornwhen prompted. Approval happens in that terminal, not in the HTTP client.
Usage examples
Append to a Google Doc
Find the document ID in the URL:
https://docs.google.com/document/d/DOCUMENT_ID/edit
curl -X POST http://127.0.0.1:8000/append_to_doc \
-H "Content-Type: application/json" \
-d '{
"doc_id": "YOUR_DOCUMENT_ID",
"content": "\nHello from the MCP server!"
}'
The server terminal will show:
Action: append_to_doc
Payload: {'doc_id': '...', 'content': '...'}
Approve? (y/n):
Type y to proceed.
Create a Gmail draft
curl -X POST http://127.0.0.1:8000/create_email_draft \
-H "Content-Type: application/json" \
-d '{
"to": "recipient@example.com",
"subject": "Test draft",
"body": "This is a draft created via the MCP server."
}'
Approve in the server terminal when prompted. Check Gmail → Drafts for the new message.
OAuth scopes
| Scope | Purpose |
|---|---|
https://www.googleapis.com/auth/documents |
Read and edit Google Docs |
https://www.googleapis.com/auth/gmail.compose |
Create and manage Gmail drafts |
Troubleshooting
| Issue | Fix |
|---|---|
credentials.json not found |
Download OAuth desktop credentials from Google Cloud Console |
Access blocked during login |
Add your account as a test user on the OAuth consent screen |
403 from API |
Type y at the approval prompt in the server terminal |
| Token errors | Delete token.json and re-authenticate |
Security notes
- Never commit
credentials.jsonortoken.json. - This server is intended for local development with manual approval.
- Do not expose it to the public internet without proper authentication.
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.