Advertise
MCP.so
Sign In
G

Google Ads MCP Server

@gomarble-ai

Repository

Basic information

Category

Developer Tools

Transports

stdio

Author

gomarble-ai

Submitted by

Akash Gupta

About Google Ads MCP Server

A FastMCP-powered Model Context Protocol server for Google Ads API integration with automatic OAuth 2.0 authentication

#google-ads#mcp-server#api-integration

Google Ads MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "google-ads": {
      "command": "/full/path/to/your/project/.venv/bin/python",
      "args": [
        "/full/path/to/your/project/server.py"
      ]
    }
  }
}

Google Ads MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Google Ads MCP Server?

A FastMCP-powered Model Context Protocol server that integrates the Google Ads API with MCP clients like Claude Desktop, featuring automatic OAuth 2.0 authentication, token refresh, GAQL query execution, and keyword research.

How to use Google Ads MCP Server?

Install Python 3.10+, clone the repository, create a virtual environment, install dependencies, configure a .env file with your Google Ads developer token and OAuth credentials path, then add the server to Claude Desktop’s claude_desktop_config.json. After a one-time browser-based OAuth flow, you can issue commands like “List all my Google Ads accounts” or run GAQL queries.

Key features of Google Ads MCP Server

  • Automatic OAuth 2.0 with one-time browser authentication
  • Smart token management with automatic refresh
  • Execute any GAQL query on Google Ads accounts
  • List and manage Google Ads accounts
  • Generate keyword ideas with search volume data
  • Built on FastMCP for modern MCP standards
  • Ready for direct integration with Claude Desktop
  • Tokens stored locally and never exposed

Use cases of Google Ads MCP Server

  • List all accessible Google Ads accounts and identify active campaigns
  • Analyze campaign performance, clicks, conversions, and costs with GAQL queries
  • Perform keyword research to discover new opportunities with search volume metrics
  • Monitor device performance breakdown across campaigns
  • Retrieve keyword-level metrics like CTR, average CPC, and quality score

Frequently asked questions

1

What does this server do that alternatives don’t?

It provides seamless OAuth 2.0 authentication and automatic token refresh, allowing you to run GAQL queries and keyword research directly from MCP clients without managing authentication manually.

2

What are the runtime dependencies?

Python 3.10+ is required, along with a Google Cloud Platform project, a Google Ads account with API access, and a developer token (initially a test token, then production access after approval).

3

Where are authentication tokens stored?

Tokens are stored locally in a `google_ads_token.json` file in the project directory; credential files are gitignored and never committed to version control.

4

How does the authentication flow work?

On first use, the server opens your browser to Google’s OAuth page. After you sign in and grant permissions, the token is saved locally and automatically refreshed when needed.

5

Are there any known limits?

The initial developer token is a test token with limited functionality. Production access requires a separate approval process through the Google Ads API Center.

Comments

More Developer Tools MCP servers

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

9

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

Final POS – Custom POS Builder

Final Commerce

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ

Nebelus

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

LastPing

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Advertise