Google Ads MCP Server
Google's first-party Model Context Protocol server for the Google Ads API. It is a Python (FastMCP) server that Google publishes as source and installs from git; Google does not operate a hosted endpoint. The server is deliberately narrow: rather than wrapping the 174 REST operations one-for-one, it exposes GAQL query construction plus field discovery, so an agent explores the reporting surface with two tools instead of memorising a schema.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport
Tools
list_accessible_customers— Returns ids of customers directly accessible by the user authenticating the call.search— Fetches data from the Google Ads API using the search method. Builds a GAQL query from structured arguments and executes it via SearchStream.get_resource_metadata— Retrieves the selectable, filterable and sortable fields for a Google Ads resource, including the metrics and segments compatible with it.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.