GSC MCP Server v2 - Remote Edition
Connects Claude AI to Google Search Console with OAuth 2.0 authentication, enabling users to analyze search performance, inspect URLs, manage sitemaps, and export analytics data through natural language conversations.
README
🔍 GSC MCP Server v2 - Remote Edition
A hosted MCP server that connects Claude AI to Google Search Console with OAuth 2.0 web authentication. Users simply sign in with Google—no API keys or credentials to manage!
✨ What's Different About v2?
| Feature | v1 (Local) | v2 (Remote) |
|---|---|---|
| Authentication | Local credentials file | OAuth 2.0 web flow |
| Setup | Complex | Just sign in with Google! |
| Hosting | Your machine | Any cloud platform |
| Multi-user | Single user | Multiple users supported |
🏗️ Architecture
┌─────────────────┐ OAuth 2.0 ┌──────────────────────┐
│ User's │ ──────────────────→│ Your Hosted │
│ Browser │←──────────────────→│ MCP Server │
└─────────────────┘ └──────────────────────┘
↓
┌─────────────────┐ MCP over SSE ┌──────────────────────┐
│ Claude Desktop │ ←─────────────────→│ Stored User Token │
└─────────────────┘ └──────────────────────┘
↓
┌──────────────────────┐
│ Google Search │
│ Console API │
└──────────────────────┘
🚀 Quick Start
1. Set Up Google OAuth (Web Application)
- Go to Google Cloud Console
- Create a new project or select existing
- Enable APIs:
- Search Console API
- Indexing API (optional)
- Go to Credentials → Create Credentials → OAuth client ID
- Select Web application
- Add authorized redirect URI:
https://your-domain.com/oauth/callback - Save your Client ID and Client Secret
2. Deploy
Option A: Railway (Easiest)
- Click the button above
- Set environment variables:
GOOGLE_CLIENT_IDGOOGLE_CLIENT_SECRETGOOGLE_REDIRECT_URI(your Railway URL +/oauth/callback)BASE_URL(your Railway URL)
Option B: Docker
# Build
docker build -t gsc-mcp-server .
# Run
docker run -p 8000:8000 \
-e GOOGLE_CLIENT_ID="your-client-id" \
-e GOOGLE_CLIENT_SECRET="your-secret" \
-e GOOGLE_REDIRECT_URI="https://your-domain.com/oauth/callback" \
-e BASE_URL="https://your-domain.com" \
-v ./data:/app/data \
gsc-mcp-server
Option C: Manual
# Clone
git clone https://github.com/AminForou/google-search-console-mcp-v2.git
cd google-search-console-mcp-v2
# Install
pip install -r requirements.txt
# Set environment variables
export GOOGLE_CLIENT_ID="your-client-id"
export GOOGLE_CLIENT_SECRET="your-secret"
export GOOGLE_REDIRECT_URI="http://localhost:8000/oauth/callback"
# Run
uvicorn gsc_server_remote:app --host 0.0.0.0 --port 8000
3. User Flow
- Users visit your server →
https://your-domain.com - Click "Sign in with Google" → OAuth flow
- Get unique API key → Displayed after login
- Configure Claude Desktop:
{
"mcpServers": {
"gscServer": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://your-domain.com/mcp/USER_API_KEY/sse"]
}
}
}
- Start chatting! → "List my GSC properties"
🛠️ Available Tools
| Tool | Description |
|---|---|
list_properties |
List all GSC properties |
get_search_analytics |
Search performance data |
get_performance_overview |
Performance summary |
find_keyword_opportunities |
Find ranking opportunities |
get_top_pages |
Top performing pages |
get_device_comparison |
Mobile vs desktop |
get_country_breakdown |
Traffic by country |
inspect_url |
URL indexing status |
get_sitemaps |
List sitemaps |
submit_sitemap |
Submit new sitemap |
request_indexing |
Request URL indexing |
export_analytics |
Export to CSV/JSON |
🔒 Security Considerations
- HTTPS Required: Always use HTTPS in production
- API Keys: Each user gets a unique key - treat it like a password
- Token Storage: Uses SQLite by default - use PostgreSQL for production
- CORS: Restrict origins in production
- Rate Limiting: Add rate limiting for production
📁 Project Structure
google-search-console-mcp-v2/
├── gsc_server_remote.py # Main server application
├── requirements.txt # Python dependencies
├── Dockerfile # Docker configuration
├── .gitignore # Git ignore rules
└── README.md # This file
🌐 Environment Variables
| Variable | Required | Description |
|---|---|---|
GOOGLE_CLIENT_ID |
✅ | OAuth client ID |
GOOGLE_CLIENT_SECRET |
✅ | OAuth client secret |
GOOGLE_REDIRECT_URI |
✅ | OAuth callback URL |
BASE_URL |
⚡ | Public server URL |
SECRET_KEY |
⚡ | Session encryption key |
DATABASE_PATH |
❌ | SQLite path (default: gsc_tokens.db) |
📊 API Endpoints
| Endpoint | Method | Description |
|---|---|---|
/ |
GET | Home page with login |
/oauth/login |
GET | Start OAuth flow |
/oauth/callback |
GET | OAuth callback |
/oauth/revoke/{user_id} |
GET | Revoke user access |
/mcp/{user_id}/sse |
GET | MCP SSE endpoint |
/health |
GET | Health check |
/api/status/{user_id} |
GET | User auth status |
🤝 Contributing
Contributions welcome! Please:
- Fork the repository
- Create a feature branch
- Submit a pull request
📄 License
MIT License - see LICENSE file.
👨💻 Author
Amin Foroutan - SEO Consultant & Developer
- 🌐 aminforoutan.com
- 📺 YouTube
⭐ If you find this useful, please star the repo!
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。