広告掲載
MCP.so
ログイン

Admob MCP Server

@ard3051997

リポジトリ

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

トランスポート

stdio

作者

ard3051997

投稿者

Abhishek Dhobe

Admob MCP Server について

MCP Server for Google AdMob — 14 tools for mediation management, revenue analysis, geo recommendations & A/B experiments via FastMCP

Admob MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "admob-mediation": {
      "command": "/path/to/MCP-admob/.venv/bin/python",
      "args": [
        "-m",
        "admob_mcp"
      ],
      "cwd": "/path/to/MCP-admob",
      "env": {
        "PYTHONPATH": "/path/to/MCP-admob",
        "PUBLISHER_ID": "pub-XXXXXXXXXXXXXXXX",
        "CREDENTIALS_PATH": "/path/to/MCP-admob/credentials.json",
        "TOKEN_PATH": "/path/to/MCP-admob/token.json",
        "AUDIT_LOG_PATH": "/path/to/MCP-admob/audit.log"
      }
    }
  }
}

Admob MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Admob Mcp?

Admob Mcp is a Model Context Protocol (MCP) server that exposes Google AdMob management, mediation waterfall operations, revenue analysis, and A/B experiments to MCP-compatible AI clients like Claude Code, Claude Desktop, Cursor, Windsurf, and Cline. It includes a local Rules Engine and Safety Layer that audits, verifies, and dry-runs mutating operations before touching the live AdMob account.

How to use Admob Mcp?

Enable the Google AdMob API in Cloud Console, download OAuth 2.0 Desktop credentials, create a Python 3.10+ virtual environment, install dependencies, configure .env with your PUBLISHER_ID and paths, run the one-time authorization flow (python admob_core/auth.py), then integrate with your AI client by specifying the command /path/to/.venv/bin/python -m admob_mcp and the required environment variables.

Key features of Admob Mcp

  • 14 MCP tools for reporting, management, experiments, and diagnostics
  • Three resources: ad‑sources, app‑categories, format‑support
  • Two prompt templates: optimize_app and portfolio_health
  • Two‑stage safety pipeline: Rules Engine validation + audit logging
  • Local SQLite database for cached metrics (admob_metrics.db)
  • Asynchronous Google AdMob REST API v1beta wrapper

Use cases of Admob Mcp

  • Run a step‑by‑step monetization audit for a single app via optimize_app(app_id)
  • Perform a portfolio‑wide health check with portfolio_health
  • Create, update, or stop mediation A/B experiments
  • Analyze root causes of fill‑rate drops, match‑rate anomalies, and revenue alerts
  • Safely manage mediation groups with dry‑run and rule‑based blocking

よくある質問

1

What are the runtime requirements for Admob Mcp?

Python 3.10 or newer, a Google Cloud project with the AdMob API enabled, OAuth 2.0 Desktop credentials, and an active AdMob publisher account.

2

How does authentication work?

OAuth 2.0 desktop flow: run `python admob_core/auth.py` to open a browser, authenticate with your Google AdMob account, and grant permissions. The resulting `token.json` is cached and auto‑refreshed on subsequent runs.

3

Where does data live?

Mediation metrics are synced into a local SQLite database (`admob_metrics.db`). Audit logs are written to `audit.log`. Credentials and tokens are stored in `credentials.json` and `token.json`.

4

What are the known limitations of the Rules Engine?

The Rules Engine blocks certain operations (e.g., adding a network that doesn’t support the ad format, using bidding networks on COPPA‑tagged apps) and warns about missing bidding partners or absent AdMob Network. All write tools support a `dry_run=True` parameter to preview changes without hitting the API.

5

How do I integrate Admob Mcp with Claude Desktop or Cursor?

For Claude Desktop, add a JSON entry to `claude_desktop_config.json` with the command, args, and environment variables. For Cursor, use the MCP settings UI to add a new command‑type server with the same command string.

コメント

「開発者ツール」の他のコンテンツ

Agent Trust (mnki-mcp)

MNKIAgentOS

Agent Trust — open profile + reference implementation for proving what an autonomous AI agent is authorized to do: identity, delegation with attenuation, proof-of-possession, attestations, tamper-evident provenance. Buil

Modelglass

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

1

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

12

Yocoolab

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

1

Rams

HSLA0001 Inc.

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url

広告掲載