AIAny
Icon for item

Google Ads MCP Server

Connects MCP-compatible AI assistants to Google Ads for account queries and reporting, with guarded support for asset creation, video uploads, and label management. It does not modify campaigns, budgets, or bids.

Introduction

An advertising agent is only as useful as its access to live account data—and only as safe as the limits on what it can change. This server bridges that gap: it exposes Google Ads reporting and reference data to MCP clients, while requiring a separate proposal and confirmation step for supported write actions.

What Sets It Apart
  • Structured Google Ads queries let an agent retrieve account performance without requiring a custom integration for every reporting question.
  • Resource metadata and reference resources help the model discover available fields, metrics, and segments, reducing guesswork when constructing queries.
  • Mutations are deliberately narrow: assets, video uploads, and labels are supported, with a checksum-bound confirmation workflow to prevent an unreviewed proposal from being committed.
  • Campaign, ad group, ad, budget, and bid changes remain out of scope. That boundary makes the server better suited to reporting and controlled account operations than to fully autonomous campaign management.
Great Fit If...

Great fit if you want an MCP client to answer questions about Google Ads accounts or handle a small set of explicitly reviewed asset and label tasks. Look elsewhere—or pair it with a separate integration—if your agent needs to create or edit campaigns, change bids, or manage budgets. Account access and the data exposed to the connected model still depend on the credentials and permissions you configure.

Information

  • Websitegithub.com
  • OrganizationsGoogle
  • Published date2025/10/03

More Items

GitHub

Inspect and measure 3D scans in the browser, compare them with CAD models, and reverse-engineer them into STEP solids. An optional MCP connection lets AI agents operate the workflow; without it, files stay local.

Hugging Face
AI Video2026

Remakes existing footage from text instructions, changing characters, props, or scenes while preserving the original motion, camera, cuts, and sound. Use it in the Viggle app or run it on your own GPUs.

GitHub
AI API2026

Provides coding agents with current guidance and resources for Gemini APIs, SDKs, and model interactions. Evaluations report API code accuracy of 87% with Gemini 3 Flash and 96% with Gemini 3.1 Pro when using these skills.