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 |
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。