Google MCP Server
Enables interaction with Google Docs and Gmail, allowing users to append text to documents and create email drafts with explicit approval prompts.
README
Google MCP Server
A Python FastAPI server that integrates with Google Docs and Gmail. Each action is printed to the terminal and requires explicit approval before it runs.
Features
| Endpoint | Description |
|---|---|
POST /append_to_doc |
Append text to a Google Doc |
POST /create_email_draft |
Create a Gmail draft |
GET /health |
Health check |
Local dev: each action is logged and prompts Approve? (y/n) in the terminal.
Production (Railway): actions are logged only; requests require the X-API-Key header matching the API_KEY secret.
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
├── README.md # This file
├── deployment-plan.md # Railway deployment guide
├── railway.toml # Railway deploy config
├── Procfile # Process start command
├── credentials.json # (NOT committed — from Google Cloud)
└── token.json # (NOT committed — auto-generated after OAuth)
Prerequisites
- Python 3.10+
- A Google Cloud project with these APIs enabled:
- Google Docs API
- Gmail API
- OAuth 2.0 Desktop client credentials downloaded as
credentials.json
Google Cloud setup
- Go to Google Cloud Console.
- Create or select a project.
- Enable Google Docs API and Gmail API under APIs & Services → Library.
- Go to APIs & Services → Credentials.
- Create OAuth client ID → Application type: Desktop app.
- Download the JSON file and save it as
credentials.jsonin this folder. - Configure the OAuth consent screen (External or Internal) and add your Google account as a test user if the app is in testing mode.
OAuth scopes
https://www.googleapis.com/auth/documentshttps://www.googleapis.com/auth/gmail.compose
Installation
cd google-mcp-server
python -m venv .venv
# Windows
.venv\Scripts\activate
# macOS / Linux
source .venv/bin/activate
pip install -r requirements.txt
Place credentials.json in the google-mcp-server/ directory.
First-time authentication
On the first API call (or when token.json is missing), a browser window opens for Google sign-in. After you approve, token.json is saved automatically. Later runs reuse that token and refresh it when needed.
Run the server
python server.py
Or:
uvicorn server:app --host 127.0.0.1 --port 8000
Interactive docs: http://127.0.0.1:8000/docs
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_DOC_ID\", \"content\": \"\\nHello from MCP server!\"}"
Watch the server terminal for the approval prompt and type y.
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\": \"Hello from the MCP server.\"}"
Approve in the terminal with y. The draft appears in Gmail under Drafts.
Railway deployment
See deployment-plan.md for the full guide. Summary:
- Push this folder to GitHub and connect it in Railway (set Root Directory to
google-mcp-serverif needed). - Set these secrets in Railway:
| Variable | Value |
|---|---|
GOOGLE_CREDENTIALS_JSON |
Full contents of credentials.json |
GOOGLE_TOKEN_JSON |
Full contents of token.json |
API_KEY |
Random secret for X-API-Key header |
ENV |
production |
- Optional: mount a Volume at
/dataand setGOOGLE_TOKEN_PATH=/data/token.jsonso refreshed tokens persist across redeploys. - Generate a public domain and call endpoints with:
curl -X POST https://YOUR-RAILWAY-URL/append_to_doc \
-H "Content-Type: application/json" \
-H "X-API-Key: YOUR_API_KEY" \
-d '{"doc_id": "YOUR_DOC_ID", "content": "\nHello from Railway!"}'
Base64 variants GOOGLE_CREDENTIALS_JSON_B64 and GOOGLE_TOKEN_JSON_B64 are also supported if JSON escaping is awkward.
Security notes
- Never commit
credentials.jsonortoken.json(they are listed in.gitignore). - In production, all mutating endpoints require a valid
X-API-Keyheader. - Revoke access anytime at Google Account permissions.
Troubleshooting
| Issue | Fix |
|---|---|
Missing credentials.json |
Download OAuth desktop credentials from Google Cloud Console |
403 access_denied on OAuth |
Add your account as a test user on the OAuth consent screen |
403 Action rejected |
You typed something other than y at the approval prompt |
| Doc append fails | Confirm the Doc ID and that the signed-in account can edit the document |
| Gmail draft fails | Confirm Gmail API is enabled and the account has Gmail access |
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.