MCP Google Ads

v1.0.0Marketing & SEOstable

An MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analy

aiclaudegoogle-adsmcpmcp-server
Share:
615
Stars
0
Downloads
0
Weekly
0/5

What is MCP Google Ads?

MCP Google Ads is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp tool that connects google ads with claude ai/cursor and others, allowing you to analyze your advertising data through natural language conversations. this integration gives you access to campaign ...

An MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analy

This server falls under the Marketing & SEO category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP tool that connects Google Ads with Claude AI/Cursor a

Use Cases

Conversational Google Ads management
Performance data analysis
Campaign strategy optimization
cohnen

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-google-ads

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Google Ads

The MCP Google Ads server connects Claude and other MCP-compatible AI clients directly to the Google Ads API, enabling natural language analysis of advertising campaigns, keywords, and performance metrics. It exposes tools such as list_accounts, get_campaign_performance, get_ad_performance, and execute_gaql_query, letting you run Google Ads Query Language queries and get formatted results without leaving your AI assistant. Marketers and analysts can quickly diagnose campaign health, spot under-performing keywords, and explore budget allocation through conversational queries.

Prerequisites

  • Python 3.10+ and uv or pip installed
  • Google Ads API Developer Token from the Google Ads API Center
  • OAuth2 credentials JSON or a service account JSON file with Google Ads access
  • A Google Ads account with at least read-level API access
  • An MCP client such as Claude Desktop or Cursor
1

Clone the repository

Download the mcp-google-ads source code from GitHub.

git clone https://github.com/cohnen/mcp-google-ads.git
cd mcp-google-ads
2

Create a virtual environment and install dependencies

Use uv to create an isolated environment and install all required packages.

uv venv .venv
source .venv/bin/activate
uv pip install -r requirements.txt
3

Configure authentication environment variables

Create a .env file with your Google Ads API credentials. GOOGLE_ADS_AUTH_TYPE controls whether OAuth or a service account is used. GOOGLE_ADS_CREDENTIALS_PATH must be an absolute path to your credentials JSON.

GOOGLE_ADS_AUTH_TYPE=oauth
GOOGLE_ADS_CREDENTIALS_PATH=/absolute/path/to/credentials.json
GOOGLE_ADS_DEVELOPER_TOKEN=your_developer_token
GOOGLE_ADS_LOGIN_CUSTOMER_ID=your_manager_account_id
4

Add the server to your MCP client configuration

Edit your Claude Desktop or Cursor configuration file to register the server. The command should point to the Python interpreter inside the virtual environment you created.

5

Restart Claude Desktop and verify tools are loaded

After restarting, open a new conversation in Claude Desktop and confirm that Google Ads tools such as list_accounts and get_campaign_performance appear in the tool list.

MCP Google Ads Examples

Client configuration

Claude Desktop configuration referencing the Python virtual environment interpreter.

{
  "mcpServers": {
    "mcp-google-ads": {
      "command": "/path/to/mcp-google-ads/.venv/bin/python",
      "args": ["/path/to/mcp-google-ads/server.py"],
      "env": {
        "GOOGLE_ADS_AUTH_TYPE": "oauth",
        "GOOGLE_ADS_CREDENTIALS_PATH": "/path/to/credentials.json",
        "GOOGLE_ADS_DEVELOPER_TOKEN": "your_developer_token",
        "GOOGLE_ADS_LOGIN_CUSTOMER_ID": "1234567890"
      }
    }
  }
}

Prompts to try

Natural-language prompts that exercise the server's ad analysis capabilities.

- "Show me all Google Ads accounts and highlight any with month-over-month spend increases over 20%"
- "Get campaign performance for account 987654321 for last week and identify campaigns below target ROAS"
- "Which ad creatives had the highest CTR last month in account 123456789?"
- "List the top 20 converting keywords with their average CPC and quality score"
- "Run a GAQL query to fetch all enabled ad groups with impressions over 1000 and format as a table"

Troubleshooting MCP Google Ads

Server fails to start with 'ModuleNotFoundError'

Ensure you activated the virtual environment before running the server, or that the command in your MCP config points to the correct .venv/bin/python path, not the system Python.

Google Ads API returns 'AuthenticationError'

Verify your credentials JSON contains valid OAuth tokens with the required Google Ads scopes. Re-run the OAuth flow to refresh expired tokens, and confirm your developer token is approved for the account type you are querying.

No accounts returned from list_accounts

If using a manager account, set GOOGLE_ADS_LOGIN_CUSTOMER_ID to the manager account ID. If using a standard account, ensure the authenticated user has API access to that account in the Google Ads UI.

Frequently Asked Questions about MCP Google Ads

What is MCP Google Ads?

MCP Google Ads is a Model Context Protocol (MCP) server that mcp tool that connects google ads with claude ai/cursor and others, allowing you to analyze your advertising data through natural language conversations. this integration gives you access to campaign information, performance metrics, keyword analy It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Google Ads?

Follow the installation instructions on the MCP Google Ads GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP Google Ads?

MCP Google Ads works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Google Ads free to use?

Yes, MCP Google Ads is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Marketing & SEO MCP Servers

Explore all marketing & seo servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-google-ads": { "command": "npx", "args": ["-y", "mcp-google-ads"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP Google Ads?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides