Can ChatGPT or Claude Manage Your Ad Accounts?

On Meta, yes. On Google, not yet. Meta runs an official ads MCP server, in open beta since 29 April 2026, and lists ChatGPT and Claude among the AI assistants that can connect to it. Once you sign in with your Meta account, the assistant can create and edit campaigns, ad sets and ads. New items start paused, the assistant asks before it turns them on, and Meta says not every account has every tool yet. Google publishes one official MCP server for the Google Ads API, and its documentation still lists it as “Read-only (current release)”: three tools that read your account and change nothing. So on Google, a chat assistant can report on a live account through official tools, but it cannot pause it, change its budgets or change its bids.

What people are actually using today is a large, fast-growing ecosystem of unofficial, developer-built MCP servers that wrap the real platform APIs with your own credentials. A live query to the GitHub Search API during our research returned 312 repositories matching “google-ads mcp” and 36 matching “facebook-ads mcp” — and exactly one of the Google-side results belongs to Google itself. With every other repo, capability and safety depend entirely on a third party’s code, and for Meta specifically, handing your access token to an unapproved third party can itself violate Meta’s Platform Terms.

This article maps what officially exists, what the community has built, the myths worth killing, and the honest gaps we could not confirm — with primary sources throughout. If what you actually want is the outcome (AI running your ads) without wiring an agent to your ad account yourself, that is the job of a purpose-built AI ad manager; we cover where that fits at the end.

What “connecting an AI to your ad account” actually means

The plumbing behind almost every “manage ads from ChatGPT/Claude” setup is the Model Context Protocol (MCP) — an open-source standard for connecting AI applications to external systems, described by the official MCP site as working “like a USB-C port for AI applications.” Anthropic announced MCP on November 25, 2024 as an open standard for secure two-way connections between data sources and AI-powered tools, and per the protocol’s own site it is supported across Claude, ChatGPT, VS Code, Cursor, and others — it is not exclusive to any one vendor.

One telling detail: OpenAI’s own MCP documentation says servers intended for ChatGPT deep research and company knowledge should implement two read-only tools — “search” and “fetch” — and gives no advertising platform as an example. Most official sources we checked lean read, not write; Meta’s ads MCP server, covered below, is the exception.

What Google officially offers — and what it refuses to do

Google ships two distinct AI developer tools for Google Ads. They are easy to conflate, and they have materially different purposes and safety models.

First, the official Google Ads MCP server, which Google describes as “a standardized bridge to the Google Ads API” that lets AI agents analyze and retrieve campaign data using natural language. Its documentation states “Mode: Read-only (current release)” and it exposes exactly three tools: list_accessible_customers (accessible customer IDs and account names), search (GAQL requests for resource metrics, budgets, and status), and get_resource_metadata (metadata about Google Ads API resource types). Setting it up requires a Google Cloud project with Explorer, Basic or Standard API access, and OAuth credentials: either an OAuth 2.0 client ID and secret, or application default credentials. Google retired developer tokens on 9 September 2026, so you no longer need one. There is no write tool. It cannot pause a campaign for you no matter how nicely you ask.

Second, the separate Gemini-powered Google Ads API Developer Assistant, which Google explicitly describes as “not a chatbot” but “a mission control system for Gemini-powered advertising engineering.” It is aimed at developers writing code against the API, not advertisers managing a live account — and on the question of changes, its install guide is blunt: “For safety, mutating operations (create, update, delete) are generated but never executed.” Google’s own AI tooling drafts the change and hands it to a human. It does not push the button.

What Meta officially offers

Meta’s Marketing API is the sanctioned way to “automate advertising across Meta technologies,” covering ad creation, management, and performance analysis. But access starts on a “Limited access” tier that Meta’s authorization docs describe as “Heavily rate-limited per ad account. For development only. Not for production apps running for live advertisers.” Full access requires passing Meta App Review, plus a usage bar: at least 500 Marketing API calls in the last 15 days, with an error rate under 15% across the last 500 calls.

Correction, 26 October 2026: an earlier version of this article said Meta publishes no official MCP server. That was wrong. Meta hosts one at mcp.facebook.com/ads. It has been in open beta since 29 April 2026, and on 16 July 2026 Meta opened it to developers who connect through their own Meta app. Its documentation says it can “create and edit ads, ad sets, and campaigns,” and it also pulls reporting, manages catalogs and reads signal health. If your business portfolio has ads MCP server rules, you can block what an agent may change, such as budgets or new campaigns. Community “Meta Ads MCP” servers still exist, but they are no longer the only way in.

Six myths about managing ads from ChatGPT or Claude

Myth 1: Google and Meta both offer an official AI connector that can change your campaigns

Only Meta does. Google’s only official MCP server is read-only with three tools, per its own documentation. Meta’s official ads MCP server can create and edit campaigns, ad sets and ads. It is in open beta, Meta says not every account has every tool yet, and new items it creates start paused until you turn them on.

Myth 2: Any “Google Ads MCP server” you find online is vetted by Google or Meta

Our GitHub Search API query returned 312 repositories matching “google-ads mcp” and 36 matching “facebook-ads mcp” at the time of checking — nearly all independent community projects (the top facebook-ads result, for example, is gomarble-ai/facebook-ads-mcp-server) that wrap the real APIs with your credentials. Exactly one repo in the Google set belongs to Google’s own organisation: googleads/google-ads-mcp, the read-only server. Our Google Ads MCP guide covers what it can and cannot do.

Myth 3: Sharing your Meta access token with a third-party MCP server is harmless

Meta’s Platform Terms (Section 6.a.iv) state: “You must protect and not transfer, share, or solicit Meta user IDs, access tokens, or app secrets,” with only a narrow exception for a Service Provider who helps you build, run, or operate your app. Handing a token to an unapproved third-party MCP server can itself be a Platform Terms violation — independent of anything the AI does with it. What follows is a description of what the platform terms say, not legal advice; if a compliance decision turns on it, have a professional read the terms with your specific setup in front of them.

Myth 4: Since it is “just API calls,” an agent can auto-adjust bids with no human checkpoint

Google’s Required Minimum Functionality policy states that all API Clients providing Creation or Management functionality must satisfy requirements related to bid adjustments, including: “End users must be able to review and edit the bid adjustments before it is set by the Google Ads API Client.” Human review of bid changes is a compliance requirement, not optional UX. We wrote more about drawing that line in what to automate and what to gate.

Myth 5: Claude’s or ChatGPT’s directories already have a ready-made Google Ads integration

Claude’s Connectors directory itself states that “Connectors in the directory are built and maintained by third-party developers using the Model Context Protocol (MCP)”, so they are not Anthropic-built. On page 1 of the 17-page directory (24 connectors, “10x Genomics Cloud” through “AppFolio Realm-X”), no Google advertising connector appeared. We could not enumerate the other 16 pages, so this is not a complete negative; verify directly before relying on it. Meta is the exception: you add its official ads MCP server to a supported assistant by its URL, mcp.facebook.com/ads, as covered above.

Myth 6: Google’s Gemini “Developer Assistant” lets you chat with your live account and have it make changes

Per Google’s own docs it is “not a chatbot” but a tool for developers writing code — and “mutating operations (create, update, delete) are generated but never executed.” It drafts change requests; a human executes them.

If you still want to wire it up: the realistic path

Step 1: Decide read-only vs. write access before anything else

For Google Ads, reporting and analysis by chat is achievable today with official tooling. Actual campaign changes — pausing, rebudgeting, bidding — are not, without building or trusting an unofficial write path. This one decision determines every step after it.

Step 2: For Google Ads read-only work, use Google’s official MCP server

Install the official server, point it at a Google Cloud project that has Explorer, Basic or Standard API access, sign in with OAuth (a client ID and secret, or application default credentials), and expect exactly three tools. There is no write tool to configure around.

Step 3: For Google Ads write access, you are building an API client, with a review queue

There is no official Google MCP write path. You need your own Google Ads API client, and its access level belongs to your Google Cloud project. New projects start on Test access, then move to Explorer (2,880 operations a day against live accounts), Basic (15,000 a day) and Standard (unlimited, with a 10-business-day review), per Google’s access levels and permissible use policy, a declared permissible-use category (ad creation and management, reporting, or keyword research), and — if your client provides Creation or Management functionality — Required Minimum Functionality compliance, including letting end users review and edit bid adjustments before they are applied.

Step 4: For Meta, use the official ads MCP server and limit what it can change

Connect Meta’s ads MCP server from a supported assistant (Meta’s ads MCP server page lists ChatGPT, Claude and Perplexity) by signing in with your Meta account. Our Meta ads MCP guide walks through the setup, the rules and what each tool can change. If your business portfolio has ads MCP server rules, block the changes you do not want an agent to make, such as budget edits, before you connect. If you are building your own app instead, the route is the Marketing API directly. Start on the default Limited access tier (development only, heavily rate-limited), then apply for Full access via App Review after logging 500+ calls in 15 days with under 15% errors, per the authorization docs.

Step 5: Treat any community MCP server as handing credentials to an unaudited third party

Hundreds exist for both platforms. Anthropic’s own support documentation warns users to “Only connect Claude to servers built and hosted by organizations and applications you trust” and to check that any action Claude takes has “no destructive or unintended effects.” For Meta tokens specifically, re-read Section 6.a.iv of the Platform Terms first. Also note that Google’s API Terms say you must not misrepresent or mask your identity when using the Google Ads API, and reserve Google’s right to monitor and audit API activity at any time.

Step 6: Check the assistant’s connector ecosystem yourself — do not assume

As of our check, page 1 of Claude’s directory showed no ads connector, and ChatGPT’s first-party connector list could not be confirmed from a primary source (the support article returned HTTP 403 on every fetch). Verify directly.

Step 7: Plan for mandatory human checkpoints on anything touching live spend

Google’s Required Minimum Functionality policy says end users must be able to review and edit bid adjustments before an API client sets them, and Google’s own AI dev tool generates mutations but never executes them. Meta’s ads MCP server starts new items paused and, where available, lets you set rules on what an agent may change. Treat those as the floor for any agent workflow you build or adopt. For comparison, here is where AdFlint’s own automation draws the line: on self-serve plans a person clicks Launch before anything goes live. After launch, autopilot makes some changes without asking. It can pause or cut spend on a clear loser, switch on new ad versions it writes, and raise a campaign budget by up to 20% at a time, with a cooldown after each raise and never past the cap you set. Every change is logged. Targeting changes and larger budget moves wait for your approval.

Step 8: Do not mistake a “runs locally” claim for a security sandbox

Google’s Developer Assistant runs generated read-only Python scripts within a “sequestered virtual environment (.venv)” — which isolates dependencies, not credentials, filesystem, or network access. The real safety control in that design is the refusal to execute mutations, not the environment it runs in.

What we could not confirm

Citation-driven research means saying where the trail went cold. Honestly, then:

• We could not enumerate pages 2–17 of Claude’s Connectors directory, so the absence of an ads connector is confirmed only for page 1. The commonly cited “400+ connectors” figure is an inference from 24 per page across 17 pages, not a number stated on the page.
• OpenAI’s support article on ChatGPT connectors returned HTTP 403 on every fetch attempt, so we have no primary-sourced list of ChatGPT’s first-party connectors — and no confirmation of whether any advertising platform appears there.
• Whether Google will add write capability to its official MCP server is unconfirmed. The docs say “Read-only (current release)” and contain no roadmap language either way — phrasing that implies it may change. Re-check before treating read-only as permanent.
• We could not fetch working primary pages for Google Ads automated rules or Meta Advantage+ campaigns, so this article makes no comparison between MCP-based access and either platform’s own in-product automation.
• The GitHub repo counts (312 and 36) drift daily; they were re-verified live during fact-checking but will differ by the time you read this.
• We did not investigate browser-automation agents that visually operate the Google Ads or Meta web UI rather than calling an API. That is a plausible real-world mechanism outside this article’s MCP-focused scope, and it could change the answer — we simply have no primary-sourced findings on it.

Where AdFlint fits

The pattern across the primary sources above: Google’s official tooling reads and drafts, and Meta’s can act, but only inside limits the account owner sets. Acting inside limits you set is also the shape of AdFlint’s AI ad management: instead of you wiring a chat assistant to raw API credentials, AdFlint connects to Google Ads and Meta through your own OAuth connection, so you own the ad account outright — no pooled provider account, a distinction that matters more than most people realize (see who owns your ad account). Hard budget caps bound what the automation can ever spend, and the autopilot keeps optimizing after launch rather than stopping at setup. You can read exactly how the pieces fit on how it works and what we do to protect your account on security.

On cost: AdFlint’s self-serve plans are a flat monthly fee with 0% markup on ad spend — your card pays Google and Meta directly — starting at $40/month for up to $1,000 in monthly ad spend, then $89 up to $2,500, $109 up to $5,000, $119 up to $10,000, $219 up to $20,000, and $319 up to $30,000, with a 7-day free trial on monthly plans (full ladder on pricing). A separate done-for-you Managed tier is a monthly fee plus a share of managed spend, priced per account, and is not self-serve. To be clear about our own limits, the same way we ask of the sources above: everything in this article comes from the cited primary documentation, not from us running these MCP servers against live accounts. If you are weighing a chat-assistant setup against a dedicated tool, our comparison of native platform AI vs. third-party tools is the right next read — and if the answer is a dedicated tool, the AI ad manager trial costs nothing for seven days.