This is not an officially supported Google product.
This is the Google Ads Model Context Protocol (MCP) server designed to provide a standardized way to integrate an LLM with Google Ads.
| Tool | Parameters | Description |
|---|---|---|
list_accounts |
Lists all available Google Ads accounts | |
search_stream |
customer_id, query |
Runs a Google Ads query |
To learn more about GAQL, try out the Google Ads Query Builder and ensure you have a valid query.
Use
this documentation
to set up a service account for the Google Ads API client library. This will
require you to also set up a Google Cloud project and enable the Google Ads API.
Create a google-ads.yaml file as defined
here.
Here's an example:
# google-ads.yaml
developer_token: INSERT_DEVELOPER_TOKEN_HERE
login_customer_id: INSERT_LOGIN_CUSTOMER_ID_HERE
json_key_file_path: JSON_KEY_FILE_PATH_HERE
use_proto_plus: trueRun the Google Ads MCP server locally:
uv run serverInstall the Gemini CLI by following the instructions here.
Add the Google Ads MCP server to your ~/.gemini/settings.json file. Here's an
example:
{
"mcpServers": {
"googleAds": {
"command": "uv",
"args": [
"--directory path/to/google_ads_mcp",
"run",
"server"
]
}
}
}Learn more about MCP servers and Gemini CLI.
Want to contribute? Learn more