AdMob MCP Server
Exposes the Google AdMob API as MCP tools for managing AdMob accounts, generating network and mediation reports, and listing apps and ad units.
README
AdMob MCP Server
This is a server that exposes the Google AdMob API as a set of tools for the Model Context Protocol (MCP).
Prerequisites
- Node.js
- npm
Installation
-
Clone the repository:
git clone https://github.com/kunny/admob-mcp-server.git cd admob-mcp-server -
Install the dependencies:
npm install -
Build the server:
npm run build
Configuration
-
Enable the AdMob API
a. Go to the Google API Console.
b. From the projects list, select a project or create a new one.
c. In the API Library, search for "AdMob API".
d. Select "AdMob API" and click the "Enable" button.
-
Create OAuth 2.0 Credentials
a. Go to the Credentials page in the Google API Console.
b. Click "Create Credentials" and select "OAuth client ID".
c. Select "Desktop app" for the "Application type".
d. Enter a name for the credential (e.g., "AdMob MCP Server").
e. Click "Create".
f. A "Client ID" and "Client Secret" will be displayed. Click "Download JSON" to download the client secret file.
-
Set up the Credentials
a. Create a
credentialsdirectory in the root of the project:mkdir credentialsb. Move the downloaded JSON file to the
credentialsdirectory and rename it toclient_secret.json. -
Set the Publisher Code (Optional)
Create a
.envfile in the root of the project and add your AdMob publisher ID:PUBLISHER_CODE=pub-xxxxxxxxxxxxxxxx
Authentication
Run the following command to authenticate with your Google account:
npm run auth
This will open a browser window for you to log in and grant permission to the application.
After you have authenticated, a token.json file will be created in the credentials directory.
Running the Server
To start the server, run the following command:
npm start
The server will be running on stdio.
Capabilities
Prompts
top_performing_apps_last7d: List top performing apps in the last 7 days, sorted by estimated earnings.top_performing_ad_units_last7d: Lists top performing ad units with estimated earnings for all mediated networks over the last 7 days, sorted by estimated earnings.
Tools
generate_network_report: Generates an AdMob Network report based on the provided report specification.generate_mediation_report: Generates an AdMob Mediation report based on the provided report specification.get_account: Gets information about the AdMob publisher account.list_ad_units: Lists the ad units under the AdMob publisher account.list_apps: Lists the apps under the AdMob publisher account.
Usage with AI Agents
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"admob": {
"command": "node",
"args": [
"{PATH_TO_SERVER}/build/index.js"
],
"env": {
"CREDENTIALS_DIR": "{PATH_TO_SERVER}/credentials",
"PUBLISHER_CODE": "pub-xxxxxxx"
}
}
}
}
Gemini CLI
Add to your ~/.gemini/settings.json:
{
"mcpServers": {
"admob": {
"command": "node",
"args": [
"{PATH_TO_SERVER}/build/index.js"
],
"env": {
"CREDENTIALS_DIR": "{PATH_TO_SERVER}/credentials",
"PUBLISHER_CODE": "pub-xxxxxxx"
}
}
}
}
License
This project is licensed under the Apache License, Version 2.0. See the LICENSE file for details.
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。