google-play-mcp-server

google-play-mcp-server

MCP server that connects AI assistants to the Google Play Developer API for automated app publishing, subscription management, review monitoring, and tester management.

Category
访问服务器

README

🎮 Google Play MCP Server

Node.js TypeScript MCP License: MIT

An MCP (Model Context Protocol) server that connects AI assistants to the Google Play Developer API v3 — enabling automated app publishing, subscription management, review monitoring, and tester management.

✨ Features

  • 📦 Publishing — List release tracks, upload AAB bundles, get store listings
  • 💰 Subscriptions & IAP — Query subscription products, base plans, pricing, and in-app products
  • ⭐ Reviews — List user reviews with ratings/device info, reply to reviews directly
  • 👥 Testers — Manage tester groups per release track
  • 🔒 Secure — Service account auth (server-to-server, no OAuth flow needed)
  • 🤖 LLM-Optimized — Markdown responses, clear error messages, proper isError flags

📋 Tools Reference

Publishing

Tool Description Read-only
gplay_list_tracks List all release tracks (internal/alpha/beta/production) with version codes, status, rollout %, and release notes
gplay_upload_bundle Upload .aab bundle → assign to track → commit. Supports draft mode and staged rollout
gplay_get_app_details Get store listing (title, descriptions, contact info) for any language

Subscriptions & IAP

Tool Description Read-only
gplay_list_subscriptions List all subscription products with base plans, billing periods, and pricing
gplay_get_subscription Get detailed subscription info including all listings, base plans, regional pricing, and offer tags
gplay_list_inapp_products List all one-time in-app products (consumable and non-consumable) with pricing

Reviews

Tool Description Read-only
gplay_list_reviews List user reviews with star ratings, review text, device info, app version, and developer replies. Supports translation
gplay_reply_review Post a developer reply to a user review (max 350 chars)

Testers

Tool Description Read-only
gplay_get_testers Get Google Group testers for a release track
gplay_update_testers Update tester Google Groups for a release track

🚀 Quick Start

1. Prerequisites

2. Google Cloud Setup

<details> <summary><strong>Step-by-step instructions</strong></summary>

  1. Create a Google Cloud project (or use an existing one)

  2. Enable the API

    • Navigate to APIs & Services → Library
    • Search for Google Play Android Developer API
    • Click Enable
  3. Create a Service Account

    • Go to IAM & Admin → Service Accounts
    • Click Create Service Account
    • Give it a name (e.g., play-console-mcp)
    • Click Create and ContinueDone
  4. Download the JSON key

    • Click on the service account you just created
    • Go to Keys tab → Add Key → Create new key → JSON
    • Save the downloaded file securely
  5. Grant Play Console access

    • Go to Google Play Console
    • Navigate to Settings → API access
    • Link your Google Cloud project (if not already linked)
    • Find your service account and click Manage permissions
    • Grant the required permissions:
      • App information (read/write) — for store listings
      • Release management (read/write) — for tracks and uploads
      • Monetization management (read-only) — for subscriptions and IAP
      • Reviews (read + reply) — for review management
    • Click Invite userSend invitation

</details>

3. Installation

# Clone the repository
git clone https://github.com/quan7794/google-play-mcp-server.git
cd google-play-mcp-server

# Install dependencies
npm install

# Build
npm run build

Or install globally via npm (once published):

npm install -g google-play-mcp-server

4. Configuration

The server requires two environment variables:

Variable Description Example
GOOGLE_SERVICE_ACCOUNT_KEY Absolute path to your service account JSON key file /home/user/.config/gcloud/play-console-key.json
GOOGLE_PLAY_PACKAGE_NAME Default Android package name for your app com.example.myapp

[!NOTE] The package_name parameter can be overridden per tool call, so you can manage multiple apps with a single server instance.

5. Add to Your MCP Client

<details> <summary><strong>Claude Desktop</strong></summary>

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "google-play": {
      "command": "node",
      "args": ["/absolute/path/to/google-play-mcp-server/dist/index.js"],
      "env": {
        "GOOGLE_SERVICE_ACCOUNT_KEY": "/path/to/service-account-key.json",
        "GOOGLE_PLAY_PACKAGE_NAME": "com.example.myapp"
      }
    }
  }
}

</details>

<details> <summary><strong>VS Code (Copilot / Cline / Continue)</strong></summary>

Add to your .vscode/mcp.json or the extension's MCP config:

{
  "servers": {
    "google-play": {
      "command": "node",
      "args": ["/absolute/path/to/google-play-mcp-server/dist/index.js"],
      "env": {
        "GOOGLE_SERVICE_ACCOUNT_KEY": "/path/to/service-account-key.json",
        "GOOGLE_PLAY_PACKAGE_NAME": "com.example.myapp"
      }
    }
  }
}

</details>

<details> <summary><strong>Cursor</strong></summary>

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "google-play": {
      "command": "node",
      "args": ["/absolute/path/to/google-play-mcp-server/dist/index.js"],
      "env": {
        "GOOGLE_SERVICE_ACCOUNT_KEY": "/path/to/service-account-key.json",
        "GOOGLE_PLAY_PACKAGE_NAME": "com.example.myapp"
      }
    }
  }
}

</details>

<details> <summary><strong>Gemini CLI / Antigravity</strong></summary>

Add to .gemini/settings.json:

{
  "mcpServers": {
    "google-play": {
      "command": "node",
      "args": ["/absolute/path/to/google-play-mcp-server/dist/index.js"],
      "env": {
        "GOOGLE_SERVICE_ACCOUNT_KEY": "/path/to/service-account-key.json",
        "GOOGLE_PLAY_PACKAGE_NAME": "com.example.myapp"
      }
    }
  }
}

</details>

💬 Usage Examples

Once connected, you can ask your AI assistant things like:

"Show me all release tracks and their current versions"
"Upload the bundle at ~/build/app-release.aab to internal testing"
"What subscriptions are configured for my app?"
"Show me recent 1-star reviews"
"Reply to review abc123 thanking them for the feedback"
"What testers are on the beta track?"

🔧 Development

npm run dev    # Watch mode with hot reload (tsx)
npm run build  # Compile TypeScript to dist/
npm run clean  # Remove dist/
npm start      # Run compiled server

Project Structure

src/
├── index.ts              # Entry point — registers tools, connects stdio
├── auth.ts               # Google Auth (service account, cached client)
├── constants.ts          # Shared constants (CHARACTER_LIMIT, tracks)
├── schemas.ts            # Shared Zod schemas (PackageNameSchema)
├── tools/
│   ├── publishing.ts     # list_tracks, upload_bundle, get_app_details
│   ├── subscriptions.ts  # list/get subscriptions, list IAP
│   ├── reviews.ts        # list/reply reviews
│   └── testers.ts        # get/update testers
└── utils/
    ├── errors.ts         # GaxiosError → LLM-friendly error messages
    └── formatter.ts      # Truncation, text content helpers

❓ Troubleshooting

<details> <summary><strong>Authentication failed (401)</strong></summary>

  • Verify GOOGLE_SERVICE_ACCOUNT_KEY points to a valid JSON key file
  • Make sure the Google Play Android Developer API is enabled in your Cloud project
  • Check that the service account hasn't been deleted or disabled

</details>

<details> <summary><strong>Permission denied (403)</strong></summary>

  • Go to Play Console → Settings → API access
  • Ensure the service account is listed and has been granted appropriate permissions
  • After granting permissions, it may take a few minutes to propagate
  • If you just invited the service account, make sure the invitation was accepted

</details>

<details> <summary><strong>Resource not found (404)</strong></summary>

  • Double-check GOOGLE_PLAY_PACKAGE_NAME matches your app's actual package name
  • Make sure the app has been published at least once (even to internal testing)
  • For subscription/IAP tools, ensure the products exist in Play Console

</details>

<details> <summary><strong>Conflict error (409)</strong></summary>

  • Another edit may be in progress — wait a few seconds and retry
  • Edits are automatically cleaned up on failure, but a manually created edit in Play Console could conflict

</details>

🔒 Security

  • Service account keys should never be committed to version control
  • Use minimal permissions — only grant what you need
  • The server runs locally via stdio — no network ports are opened
  • All API calls use OAuth 2.0 with the androidpublisher scope

🤝 Contributing

Contributions are welcome! Please:

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-tool)
  3. Make your changes, ensuring npm run build passes
  4. Submit a Pull Request

Adding a New Tool

  1. Add the tool registration in the appropriate file under src/tools/
  2. Use withErrorHandling() wrapper for consistent error handling
  3. Use textContent() and truncateIfNeeded() for responses
  4. Add proper Zod schemas with .describe() for all parameters
  5. Set correct annotations (readOnlyHint, destructiveHint, etc.)
  6. Update this README

📄 License

MIT © Waclabs


Built with ❤️ using Model Context Protocol and the Google Play Developer API v3.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选