# AdCopilot

> A hosted Google Ads MCP server. It connects an AI assistant you already use —
> Claude, ChatGPT, Copilot, Gemini CLI or any other MCP client — to your Google
> Ads account through your own Google sign-in, so the assistant can read the
> account and, if you enable it, change it. Built on the open-source Google Ads
> MCP server published by Google under Apache 2.0, extended from 3 read tools to
> 36, hosted, with the 4 destructive tools removed.

Published by Atromx Intelligence (https://atromx.com). Not affiliated with,
endorsed by or sponsored by Google, Anthropic or OpenAI.

Distinct from "AdsCopilot" (adscopilot.com), an unrelated browser extension.

## Product

- [AI agent for Google Ads](https://adcopilot.cloud/ai-agent-for-google-ads): Definition of an AI agent for Google Ads, how it differs from Smart Bidding and automated recommendations, the read/write boundary, and what to check before granting one access.
- [Autonomous agents](https://adcopilot.cloud/autonomous-google-ads-agent): Levels of autonomy in Google Ads management, which optimisation work is safe unattended versus which needs approval, and why irreversible actions should not be automated.
- [Google Ads MCP server](https://adcopilot.cloud/google-ads-mcp-server): What a Google Ads MCP server is, how Google's official open-source server compares to a hosted one, the full tool list AdCopilot exposes, and what you need to connect.
- [For agencies and teams](https://adcopilot.cloud/for-agencies): How agencies and in-house teams share a Google Ads AI connector: per-member Google sign-in, seats, per-person switch-off, account scoping and an audit trail.
- [AI Google Ads audit](https://adcopilot.cloud/google-ads-audit-ai): How to audit a Google Ads account with an AI assistant: the checks that matter, the exact questions to ask, wasted-spend patterns, and which of Google's own recommendations to distrust.
- [Google Ads automation](https://adcopilot.cloud/google-ads-automation): The layers of Google Ads automation from Smart Bidding to scripts to AI agents, what each layer decides, what none of them will do, and what to automate first.
- [Negative keywords](https://adcopilot.cloud/negative-keywords-automation): How to automate negative keywords: the three negative match types, account, campaign, ad group and shared list placement, the intent patterns worth blocking, and how an AI connector applies them.
- [Performance Max AI](https://adcopilot.cloud/performance-max-ai): What is visible and controllable in a Performance Max campaign, what an AI agent can genuinely do including creating PMax campaigns and asset groups, and where it cannot help.

## Connecting a client

- [Connect Claude](https://adcopilot.cloud/connect-claude-to-google-ads): Step-by-step instructions for adding a Google Ads MCP connector to Claude Desktop, claude.ai and Claude Code, including what to ask it first and how to revoke access.
- [Connect ChatGPT](https://adcopilot.cloud/connect-chatgpt-to-google-ads): Step-by-step instructions for adding a Google Ads MCP connector to ChatGPT, what it can read and change, and how to withdraw access.
- [Copilot, Gemini, Cursor](https://adcopilot.cloud/mcp-clients): How to add a Google Ads MCP connector to GitHub Copilot, Gemini CLI, Cursor, OpenCode and Claude Code, including the exact configuration each client expects.
- [API access and tokens](https://adcopilot.cloud/google-ads-api-access): What a Google Ads developer token is, how it differs from OAuth credentials, the test, basic and standard access levels, what else self-hosting needs, and when a hosted connector removes the need.

## Security and data

- [Security and data](https://adcopilot.cloud/security): Security model for connecting an AI assistant to Google Ads: OAuth scope, encrypted refresh tokens, destructive tools removed, account scoping, audit trail, rate limits and revocation.


## More

- [All guides](https://adcopilot.cloud/guides): the index of everything below, grouped by the question it answers.
- [Home and free pilot](https://adcopilot.cloud/): what the product does, and how to start a one-week read-only pilot on one account.
- [Canonical facts](https://adcopilot.cloud/llms-full.txt): dense factual summary — tool counts, tiers, limits, what is and is not claimed.