Google Ads MCP Server

The Google Ads MCP Server is an implementation of the Model Context Protocol (MCP) that enables Large Language Models (LLMs), such as Gemini, to interact directly with the Google Ads API.

[!NOTE] This is NOT an officially supported Google product. It is mainly for experimental purposes and not intended for production use. Consider using the official Google Ads MCP Server instead.

Disclaimer

Copyright Google LLC. Supported by Google LLC and/or its affiliate(s). This solution, including any related sample code or data, is made available on an “as is,” “as available,” and “with all faults” basis, solely for illustrative purposes, and without warranty or representation of any kind. This solution is experimental, unsupported and provided solely for your convenience. Your use of it is subject to your agreements with Google, as applicable, and may constitute a beta feature as defined under those agreements. To the extent that you make any data available to Google in connection with your use of the solution, you represent and warrant that you have all necessary and appropriate rights, consents and permissions to permit Google to use and process that data. By using any portion of this solution, you acknowledge, assume and accept all risks, known and unknown, associated with its usage and any processing of data by Google, including with respect to your deployment of any portion of this solution in your systems, or usage in connection with your business, if at all. With respect to the entrustment of personal information to Google, you will verify that the established system is sufficient by checking Google's privacy policy and other public information, and you agree that no further information will be provided by Google.

Getting Started

Follow these instructions to configure and run the Google Ads MCP Server.

1. Configure Python Environment

For Direct Use

This project needs Python 3.12 with pipx or uv.

For Development

This project uses uv for dependency management.

Install uv and then run the following command to install the required Python packages:

uv pip sync

2. Configure Google Ads credentials

This tool requires you to have a google-ads.yaml file with your Google Ads API credentials. By default, the application will look for this file in your home directory.

If you don't have one, you can generate it by running the following example from the google-ads-python library: authentication example

Make sure your google-ads.yaml file contains the following keys:

• client_id
• client_secret
• refresh_token
• developer_token
• login_customer_id (optional, but recommended)

3. Configuration

The server can be configured using the following environment variables:

• ADS_MCP_ENABLE_MUTATIONS: Set to true to enable mutation tools. Defaults to false.
• GOOGLE_ADS_CREDENTIALS: Path to the google-ads.yaml file.
• USE_GOOGLE_OAUTH_ACCESS_TOKEN: Set to enable Google OAuth token verification.

4. Launch MCP Server

For Direct Use with Gemini CLI

Update your Gemini configuration to include the google-ads-mcp server. The following is an example of a local MCP server configuration:

{
  // Other configs...
  mcpServers: {
    GoogleAds: {
      command: "pipx",
      args: [
        "run",
        "--spec",
        "git+https://github.com/google-marketing-solutions/google_ads_mcp.git",
        "run-mcp-server",
      ],
      env: {
        GOOGLE_ADS_CREDENTIALS: "PATH_TO_YAML",
      },
      timeout: 30000,
      trust: false,
    },
  },
}

Once the server is running, you can interact with it using the Gemini CLI. Type /mcp in Gemini to see the Google Ads API server listed in the results.

For Local

... View full README on GitHub