Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

google-ads-mcp

google-ads-mcp: An MCP server that interacts with the Google Ads API and provides tools and resources for LLMs and AI agents.

What problem it solves

LLMs and AI agents need structured access to Google Ads account data, API metadata, and management operations. The server provides this access through MCP while adding a two-step proposal and confirmation workflow for write operations.

Key features

  • Query Google Ads accounts — Use GAQL to retrieve information about a Google Ads account, list directly accessible customers, and inspect Google Ads API resource metadata.

    Source: README

  • Manage assets and labels — Create assets, upload local videos, manage account labels, and create or remove label associations on supported Google Ads resources.

    Source: README

  • Confirm changes safely — Mutating tools first validate proposed changes and return a checksum. A subsequent mutation requires the same parameters and the returned checksum after explicit user approval.

    Source: README

  • Configure available tools — `tools_config.yaml` can enable or disable tools and categories, customize namespace prefixes, or produce a strictly read-only deployment.

    Source: README, ads_mcp

  • Support local and remote deployment — The server can run through an MCP client with local credentials or use FastMCP's OAuth proxy and Streamable HTTP for dynamic authentication and shared web-service deployments.

    Source: README

Quick start

Copied verbatim from the project's README.

pipx run --spec "google-ads-mcp==X.Y.Z" google-ads-mcp
  what can the ads-mcp server do?

Who it may suit

This may suit developers and end users who want an LLM or AI agent to query and manage Google Ads accounts through MCP.

Topics to discuss

  • Which Google Ads workflows should receive additional MCP tools or resources?

  • How should the Propose & Confirm workflow evolve for different mutation risks?

  • What configuration and deployment scenarios should the project prioritize next?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/googleads/google-ads-mcp#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/googleads/google-ads-mcp

Comments

…