mcp-google-ads and google_ads_mcp
These are competitors—both implement MCP servers that connect Google Ads APIs to LLMs, with the cohnen version being more mature and community-adopted (453 stars vs. 125, active downloads vs. none), while the official Google implementation appears to be an alternative approach to the same integration problem.
About mcp-google-ads
cohnen/mcp-google-ads
An MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analytics, and ad management—all through simple chat with Claude, Cursor or Windsurf.
Implements FastMCP server architecture with OAuth 2.0 and service account authentication, exposing tools like `execute_gaql_query` and `run_gaql` for direct Google Ads Query Language access alongside pre-built performance analytics. Supports automatic token refresh, multiple authentication methods, and integrates with Claude, Cursor, and Windsurf via the Model Context Protocol standard.
About google_ads_mcp
google-marketing-solutions/google_ads_mcp
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.
Exposes Google Ads API capabilities through MCP tools, allowing LLMs to query campaigns, ad groups, and performance metrics via natural language. Built as a Python server using the MCP protocol, it authenticates via OAuth 2.0 credentials stored in `google-ads.yaml` and integrates with Gemini CLI through stdio transport. Designed for both direct deployment via `pipx` and local development workflows using `uv` for dependency management.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work