Google Ads MCP
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
What is Google Ads MCP?
Google Ads MCP 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
Maintainer
Works with
Installation
Manual Installation
npx google-ads-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Google Ads MCP
The Google Ads MCP server bridges Claude AI and the Google Ads API, letting you query campaign data, keyword performance, and ad metrics through natural language conversations. It exposes tools like list_accounts, get_campaign_performance, and execute_gaql_query so you can run Google Ads Query Language queries directly from Claude. This is ideal for marketers and analysts who want to explore ad performance data without writing GAQL or navigating the Google Ads UI manually.
Prerequisites
- Python 3.10+ and uv or pip installed
- Google Ads API access with a Developer Token from the Google Ads API Center
- OAuth2 credentials or a service account JSON for Google Ads authentication
- A Google Ads account (manager or standard) with at least read access
- An MCP client such as Claude Desktop or Cursor
Clone the repository
Clone the mcp-google-ads repository from GitHub and enter the project directory.
git clone https://github.com/cohnen/mcp-google-ads.git
cd mcp-google-adsCreate and activate a virtual environment
Create an isolated Python environment using uv (recommended) or the built-in venv module.
uv venv .venv
source .venv/bin/activate # macOS/Linux
# .venv\Scripts\activate # WindowsInstall dependencies
Install the required Python packages into the virtual environment.
uv pip install -r requirements.txtSet environment variables
Create a .env file in the project root with your Google Ads credentials. GOOGLE_ADS_AUTH_TYPE should be either 'oauth' or 'service_account'. Set GOOGLE_ADS_CREDENTIALS_PATH to the path of your OAuth or service account JSON file. GOOGLE_ADS_DEVELOPER_TOKEN is your API developer token, and GOOGLE_ADS_LOGIN_CUSTOMER_ID is optional and used when accessing sub-accounts through a manager account.
GOOGLE_ADS_AUTH_TYPE=oauth
GOOGLE_ADS_CREDENTIALS_PATH=/path/to/credentials.json
GOOGLE_ADS_DEVELOPER_TOKEN=your_developer_token_here
GOOGLE_ADS_LOGIN_CUSTOMER_ID=1234567890Configure your MCP client
Add the server entry to your Claude Desktop or Cursor configuration file. On macOS the Claude Desktop config lives at ~/Library/Application Support/Claude/claude_desktop_config.json.
Restart your MCP client
Restart Claude Desktop or Cursor to load the new server configuration. The Google Ads tools should appear in the available tools list.
Google Ads MCP Examples
Client configuration
Add this block to claude_desktop_config.json, replacing paths and credentials with your own values.
{
"mcpServers": {
"google-ads-mcp": {
"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_here",
"GOOGLE_ADS_LOGIN_CUSTOMER_ID": "1234567890"
}
}
}
}Prompts to try
Example natural-language queries you can send once the server is connected.
- "List all my Google Ads accounts and show which spent the most this month"
- "Show me the top 10 campaigns for account 123456789 over the last 30 days sorted by ROAS"
- "Analyze desktop vs mobile performance across all campaigns and suggest bid adjustments"
- "Find keywords with quality scores below 5 that are still active and have spend over $100"
- "Run this GAQL query and return results as CSV: SELECT campaign.name, metrics.clicks FROM campaign WHERE segments.date DURING LAST_30_DAYS"Troubleshooting Google Ads MCP
Authentication error: 'DEVELOPER_TOKEN_NOT_APPROVED'
Your Google Ads Developer Token may be in 'test account' mode. Apply for basic or standard access in the Google Ads API Center, or use a test account while in approval.
Credentials file not found or permission denied
Verify GOOGLE_ADS_CREDENTIALS_PATH points to the correct absolute path and that the file is readable by the process. If using OAuth, ensure the credentials JSON includes refresh_token, client_id, and client_secret fields.
GAQL query returns no results
Google Ads GAQL requires correct resource/field combinations. Check that your date range includes data and that the account ID (GOOGLE_ADS_LOGIN_CUSTOMER_ID) matches the account you're querying.
Frequently Asked Questions about Google Ads MCP
What is Google Ads MCP?
Google Ads MCP 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 Google Ads MCP?
Follow the installation instructions on the Google Ads MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Google Ads MCP?
Google Ads MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Google Ads MCP free to use?
Yes, Google Ads MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Google Ads MCP Alternatives — Similar Marketing & SEO Servers
Looking for alternatives to Google Ads MCP? Here are other popular marketing & seo servers you can use with Claude, Cursor, and VS Code.
TopRank
★ 2.6kGoogle Ads analysis and operations — read performance, manage keywords, bids, and campaigns.
Open SEO
★ 2.1kOpen source alternative to Semrush and Ahrefs
ASO Skills
★ 1.4kAI agent skills for App Store Optimization (ASO) and app marketing. Built for indie developers, app marketers, and growth teams who want Cursor, Claude Code, or any Agent Skills-compatible AI assistant to help with keyword research, metadata optimiza
Google Meta Ads GA4
★ 994MCP server for Google Ads, Meta Ads & GA4 — works with ChatGPT, Claude, Cursor, n8n, Windsurf & more. 250+ tools for campaign management, analytics & optimization.
Meta Ads
★ 923A Model Context Protocol server that allows AI models to access, analyze, and manage Meta advertising campaigns, enabling LLMs to retrieve performance data, visualize ad creatives, and provide strategic insights for Facebook and Instagram platforms.
Google Search Console
★ 882Connects Google Search Console with Claude AI to enable SEO professionals to analyze their SEO data through natural language conversations, providing access to property information, search analytics, URL inspection, and sitemap management.
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.
Set Up Google Ads MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Google Ads MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.