io.github.henilcalagiya/google-sheets-mcp
编码与调试by henilcalagiya
Powerful tools for automating Google Sheets using Model Context Protocol (MCP)
什么是 io.github.henilcalagiya/google-sheets-mcp?
Powerful tools for automating Google Sheets using Model Context Protocol (MCP)
README
Google Sheets MCP Server
Powerful tools for automating Google Sheets using Model Context Protocol (MCP)
mcp-name: io.github.henilcalagiya/google-sheets-mcp
Overview
Google Sheets MCP Server provides seamless integration of Google Sheets with any MCP-compatible client. It enables full spreadsheet automation — including creating, reading, updating, and deleting sheets — through a simple and secure API layer.
Features
- Full CRUD support for Google Sheets and tables
- Works with Continue.dev, Claude Desktop, Perplexity, and other MCP clients
- Secure authentication via Google Service Account
- Comprehensive tools for Google Sheets automation
- Automatic installation via
uvx
Requirements
- Python 3.10+
uvpackage manager (foruvxcommand)- A Google Cloud project with a Service Account
- MCP-compatible client (e.g., Continue.dev)
Install uv:
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows PowerShell
irm https://astral.sh/uv/install.ps1 | iex
Quick Start
1. Set Up Google Service Account
Step 1: Create a Google Cloud Project
- Go to Google Cloud Console
- Click "Select a project" → "New Project"
- Enter a project name (e.g., "my-sheets-automation")
- Click "Create"
Step 2: Enable Required APIs
- In your project, go to "APIs & Services" → "Library"
- Search for "Google Sheets API" → Click → "Enable"
- Search for "Google Drive API" → Click → "Enable"
Step 3: Create Service Account
- Go to "IAM & Admin" → "Service Accounts"
- Click "Create Service Account"
- Enter service account name (e.g., "sheets-mcp-service")
- Click "Create and Continue"
- Skip role assignment → Click "Continue"
- Click "Done"
Step 4: Generate JSON Key
- Click on your new service account email
- Go to "Keys" tab → "Add Key" → "Create new key"
- Choose "JSON" format → Click "Create"
- The JSON file will download automatically
Step 5: Extract Required Values Open the downloaded JSON file and note these values:
project_id(e.g., "my-sheets-automation-123456")private_key_id(e.g., "a4ae73111b11b2c3b07cc01006e71eb8230dfa29")private_key(the long private key starting with "-----BEGIN PRIVATE KEY-----")client_email(e.g., "sheets-mcp-service@my-sheets-automation-123456.iam.gserviceaccount.com")client_id(e.g., "113227823918217958816")client_x509_cert_url(e.g., "https://www.googleapis.com/robot/v1/metadata/x509/sheets-mcp-service%40my-sheets-automation-123456.iam.gserviceaccount.com")
Example Google service account JSON structure:
{
"type": "service_account",
"project_id": "your-project-id",
"private_key_id": "your-private-key-id",
"private_key": "-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----\n",
"client_email": "your-service@your-project.iam.gserviceaccount.com",
"client_id": "your-client-id",
"auth_uri": "https://accounts.google.com/o/oauth2/auth",
"token_uri": "https://oauth2.googleapis.com/token",
"auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
"client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/your-service%40your-project.iam.gserviceaccount.com"
}
2. Configure MCP Client
{
"mcpServers": {
"google-sheets-mcp": {
"command": "uvx",
"args": ["google-sheets-mcp@latest"],
"env": {
"project_id": "your-project-id",
"private_key_id": "your-private-key-id",
"private_key": "-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----\n",
"client_email": "your-service@your-project.iam.gserviceaccount.com",
"client_id": "your-client-id",
"client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/your-service%40your-project.iam.gserviceaccount.com"
}
}
}
}
💡 Pro Tip: You can copy the values directly from your Google service account JSON file. The field names in the JSON file are used exactly as they are - no changes needed!
🔄 Backward Compatibility: The server also supports the old GOOGLE_ prefixed variable names (e.g., GOOGLE_PROJECT_ID) for existing configurations.
3. Share Your Google Sheet with the Service Account
- Open your target Google Spreadsheet in your web browser.
- Click the Share button.
- Enter the service account email (e.g.,
your-service@your-project.iam.gserviceaccount.com) and assign Editor access. - Click Send to provide editor permissions.
🎉 You're all set! Your MCP client will automatically install and run the package when needed.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Author
Henil C Alagiya
- GitHub: @henilcalagiya
- LinkedIn: Henil C Alagiya
Support & Contributions:
- 🐛 Report Issues: GitHub Issues
- 💬 Questions: Reach out on LinkedIn
- 🤝 Contributions: Pull requests welcome!
常见问题
io.github.henilcalagiya/google-sheets-mcp 是什么?
Powerful tools for automating Google Sheets using Model Context Protocol (MCP)
相关 Skills
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。