How to set up the Model Context Protocol (MCP) server for Google Ads

Before you begin

To set up the Google Ads MCP server, you will need:

• An AI app or agent (in our case, it is the Claude app).

How to configure the MCP server for Google Ads

1. Open Claude Desktop and go to Settings → Developer → Edit Config → open desktop JSON file called claude_desktop_config.

This opens Claude’s JSON configuration file, which is where Claude stores information about the MCP servers it can connect to. Every MCP server that you want Claude to use must be defined in this configuration file.

2. Add the following configuration (remove any existing configs):

3. Save the changes in the file.

4. Restart Claude Desktop. After restarting, a browser window will open. Choose the Google account that has access to the Google Ads property you want to modify using the MCP server by Stape. Complete the authentication process to grant Claude access to your MCP server.

After the access is granted, you’ll get the message “Authorization successful! You may close this window and return to the CLI”. It means that the tool will be available for your use. In Settings → Developer, you will see the status Running next to google-ads-mcp. If you face any problems with configuration, refer to the troubleshooting section further in this guide.

5. After the access is granted, the tool will be available for your use.

6. Now you can type your request via chat. To verify that it’s working, just type any query related to your Google Ads account, like “List all my Google Ads campaigns” or “What's the total spend across all campaigns this month?”

Using the Google Ads MCP Server with a CLI

If you prefer working in the terminal rather than a desktop app, it’s pretty simple. For instance, you can add the Google Ads MCP server to Claude Code with a single command:

That's it. Claude Code will handle the OAuth authentication flow automatically when you first use the server – a browser window will open for you to log in and grant access, just like with Claude Desktop.

To confirm the server was added successfully, run:

You should see google-ads-mcp in the output with its URL.

Testing

To check that everything works as intended, simply enter a request in your AI app and see if it’s completed correctly within the GA4 environment.

MCP Server name length limit

Some MCP clients, like Cursor AI, enforce a 60-character limit on the combined length of the MCP server name and the tool name. If your configuration uses a long server name (e.g., google-ads-mcp-your-additional-long-name), this may cause specific tools to be hidden or filtered out by the client.

Action: to ensure all tools are visible, configure your MCP server with a shorter name (e.g., google-ads-mcp).

The MCP cache

mcp-remote stores credential data in ~/.mcp-auth (or the location defined by the $MCP_REMOTE_CONFIG_DIR$ environment variable). If you run into persistent issues, you should try clearing this cached state and tokens.

Use this command to clear the cache:

Afterward, restart your MCP client.