Skip to content
Google Ads MCP

Google Ads MCP

by Google
Released
v0.0.3
Apache-2.0
Repository Docs
Payments & Commerce

Summary

Google's own MCP server for the Google Ads API: run GAQL queries, inspect resource metadata and list the accounts your credentials can reach.

Features

  • First-party server from the Google Ads team
  • GAQL `search` tool covering every reportable Google Ads resource
  • `get_resource_metadata` so the agent discovers fields before querying
  • `list_accessible_customers` for account discovery
  • Resources for the discovery document, metrics, segments and release notes
  • Per-tool enable/disable via tools_config.yaml
  • OAuth proxy, Application Default Credentials or google-ads.yaml auth

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it, filling in the environment variables with your own values.
  3. Restart the agent — the "Google Ads MCP" tools will be available.
{
  "mcpServers": {
    "google-ads-mcp": {
      "command": "pipx",
      "args": [
        "run",
        "--spec",
        "google-ads-mcp==0.0.3",
        "google-ads-mcp"
      ],
      "env": {
        "GOOGLE_PROJECT_ID": "your-gcp-project-id",
        "GOOGLE_ADS_DEVELOPER_TOKEN": "your-developer-token"
      }
    }
  }
}

Description

Published by the Google Ads team, this is the first-party MCP server for the Google Ads
API. It is deliberately narrow: rather than wrapping hundreds of endpoints in hundreds of tools, it
exposes the query language the API is actually built around and lets the model compose from there.

Tools

  • search — runs a GAQL query against an account and returns the rows. This is the workhorse:

campaign structure, ad groups, keywords, spend, conversions and any other reportable resource all
come back through it.

  • get_resource_metadata — returns the schema for a Google Ads API resource type, so the agent can

discover which fields and segments exist before writing a query instead of guessing at them.

  • list_accessible_customers — returns the customer IDs the authenticated user can reach directly.

It also serves MCP resources: the API discovery document, the metrics and segments catalogues, and
the Google Ads API release notes.

Authentication. Three paths, depending on how you run it. A FastMCP OAuth proxy is the
recommended route for a hosted deployment; Application Default Credentials work locally if you have
authenticated gcloud with the adwords scope; or it can read an existing google-ads.yaml from
the Google Ads API Python client library. A developer token with at least Explorer access is
required for production accounts.

Configuration. tools_config.yaml enables or disables tools individually — useful when you want
a read-only surface. Environment variables cover GOOGLE_PROJECT_ID,
GOOGLE_ADS_DEVELOPER_TOKEN and, for manager accounts, GOOGLE_ADS_LOGIN_CUSTOMER_ID.

Published on PyPI as google-ads-mcp and licensed Apache-2.0.

Related MCP Servers

MCP: Meta Ads MCP

by Meta

Meta's hosted MCP server for Facebook and Instagram advertising: reporting, campaign and creative writes, catalogues, signal health and lift studies.

Payments & Commerce

MCP: X Ads MCP

by X Corp.

X's official remote MCP server for advertisers — 23 tools to read campaign data, run analytics and create or activate campaigns from any MCP client.

Payments & Commerce

MCP: Data Commons MCP Server

by Data Commons

Query public statistics — health, economic, demographic and climate indicators from hundreds of official sources — through the Data Commons knowledge graph, hosted or self-run.

Databases & Data
Browse all MCP servers →