ads-mcp

ads-mcp

Enables querying mobile ad revenue from Google AdMob and Huawei Petal Ads through natural language, with read-only tools for account, app, ad unit, and revenue reports.

Category
Visit Server

README

ads-mcp

A Model Context Protocol server that puts your mobile ad revenue in one conversational interface: Google AdMob and Huawei Petal Ads (Publisher Service), side by side.

Ask Claude things like:

"How much did I earn across AdMob and Petal Ads last week?"
"Which AdMob ad units are underperforming?"
"Break down my Petal Ads revenue by app"
"Compare yesterday's eCPM by country"

Tools

Tool Network Description
admob_list_accounts AdMob List publisher accounts
admob_get_account AdMob Account details (currency, timezone)
admob_list_apps AdMob List apps (paginated)
admob_list_ad_units AdMob List ad units (paginated)
admob_network_report AdMob Network report with full dimension/metric/filter/sort control
admob_mediation_report AdMob Mediation report (per ad-source performance)
petal_report Petal Ads Publisher report with full group-by/filter/order/pagination control
petal_revenue_summary Petal Ads Daily earnings trend + totals for a date range
petal_apps_performance Petal Ads Per-app (and per-placement) earnings breakdown
ads_revenue_overview Both Combined totals + daily breakdown across both networks
ads_auth_status Both Check which networks are configured/authorized

All tools are read-only — this server never mutates your ad accounts.

Prerequisites

  • Node.js 18+
  • For AdMob: a Google Cloud project with the AdMob API enabled and an OAuth 2.0 Desktop app client
  • For Petal Ads: a HUAWEI Developers OAuth client with the Publisher Service Reporting API (Ads Kit) enabled

Setup

1. Install and build

git clone https://github.com/qalvinahmad/ads-mcp.git
cd ads-mcp
npm install
npm run build
cp .env.example .env

2. Google AdMob

  1. Open Google Cloud Console → select/create a project.
  2. Enable the AdMob API in the API Library.
  3. APIs & Services → Credentials → Create Credentials → OAuth client ID → Desktop app, then download the JSON.
  4. Save it as secrets/client_secret.json (or point ADMOB_CLIENT_SECRET_PATH in .env at it).
  5. Run the one-time authorization (opens a browser):
npm run auth:admob

If your OAuth consent screen is in "Testing" status, add your Google account as a test user (otherwise you'll get an authorization error, and refresh tokens expire after 7 days).

3. Huawei Petal Ads

  1. Open HUAWEI Developers Console → HMS API Services → Credentials.
  2. Create an OAuth 2.0 client ID (server type) with the Ads Kit / Publisher Service Reporting API enabled.
  3. Put the credentials in .env:
HUAWEI_CLIENT_ID=your_client_id
HUAWEI_CLIENT_SECRET=your_client_secret

Or, if you keep them as a single combined key:

HUAWEI_ADS_API_KEY=client_id:client_secret

No browser flow is needed — Petal Ads uses OAuth client-credentials (server-to-server).

4. Verify

npm run doctor    # checks both networks; tests the Huawei token endpoint
npm run smoke     # boots the server and validates the MCP handshake + tool list

Register with an MCP client

Claude Code (CLI)

claude mcp add ads -- node /absolute/path/to/ads-mcp/dist/index.js

Claude Desktop

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

{
  "mcpServers": {
    "ads": {
      "command": "node",
      "args": ["/absolute/path/to/ads-mcp/dist/index.js"]
    }
  }
}

Cursor / Windsurf / Cline

"ads": {
  "command": "node",
  "args": ["/absolute/path/to/ads-mcp/dist/index.js"]
}

Configuration is read from ads-mcp/.env automatically (the server resolves it relative to its own install directory, not the client's working directory).

Environment variables

Variable Default Description
ADMOB_CLIENT_SECRET_PATH secrets/client_secret.json Google OAuth Desktop-app client JSON
ADMOB_TOKEN_PATH secrets/admob-token.json Cached authorized user token
ADMOB_OAUTH_PORT 8089 Localhost port for the one-time OAuth flow
HUAWEI_CLIENT_ID / HUAWEI_CLIENT_SECRET — Huawei OAuth client (preferred)
HUAWEI_ADS_API_KEY — Combined client_id:client_secret fallback
HUAWEI_DEFAULT_CURRENCY USD Default report currency (CNY, USD, EUR)
HUAWEI_OAUTH_TOKEN_URL Huawei production Override for testing
HUAWEI_ADS_REPORT_URL Huawei production Override for testing

Security notes

  • secrets/ and .env are gitignored — never commit credentials.
  • The AdMob token file is written with 0600 permissions.
  • Huawei access tokens are cached in memory only.
  • All tools are read-only against both ad networks.

API references

Credits

License

MIT — see LICENSE.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured