Time Booster
A table of what the Google Ads MCP server can do. It reads campaigns, keywords, search terms and conversion actions. It can't change bids, budgets or ads, and it can't see GA4 or the CRM.
Paid ads· 9 min read

Google Ads MCP server: what it can do, what it can't, and how to connect it

Google's free Google Ads MCP server lets Claude or ChatGPT read your accounts. What it can do, what it can't, and how to connect it, step by step.

Ivan Tsekov

Written by

Ivan Tsekov

Founder, Time Booster

Before building growth engines that AI agents keep running, Ivan spent more than 10 years in performance marketing: Google Ads, Meta ads, email and funnels for B2B and B2C companies, with over €5M in ad spend managed and the full funnel owned from first click to closed deal.

Follow on LinkedIn

On this page
  1. 1.What the Google Ads MCP server can do
  2. 2.A first-read prompt to paste into Claude or ChatGPT
  3. 3.What it can't do, and how to keep the account safe
  4. 4.How to make changes, add GA4 and run daily checks
  5. 5.How to connect it to Claude or ChatGPT on your computer
  6. 6.How to connect it to Claude or ChatGPT in the browser
  7. 7.Questions people ask

Google's Google Ads MCP server is a free tool that connects Claude, ChatGPT or another AI assistant to your Google Ads accounts. You ask a question in plain words, and it pulls the numbers and answers. It reads the account, but it can't change anything in it.

MCP is an open standard for connecting AI assistants to other tools, and this is Google's own server for it. I've managed €5M+ of ad spend over 10+ years, and I always read an account before I touch it.

In short:

  • It reads campaigns, search terms and conversions in every account your login opens, and it can't change anything.
  • It only sees Google Ads, so it can't tell you whether a sale really happened.
  • For changes, we add our own connection next to it. Claude asks, you say yes, and it makes the change and checks it.
  • Setup is a Google Cloud project with Explorer access, an OAuth client, one sign-in command and one block in your AI app.

What the Google Ads MCP server can do

It reads your data in every account your Google login opens, including the ones under your manager account. Google lists more than 180 kinds of data it can pull, for example:

  • campaigns, ad groups, keywords and ads, with their numbers;
  • the search terms report;
  • your conversion actions, and what each one counts;
  • budgets, bid strategies and targets;
  • Performance Max, Shopping, landing pages and locations.

So you can ask it what you'd ask a colleague, such as "Which search terms cost money and never converted?"

Just reading an account is worth a lot, whatever connects the AI to it.

On one of my own accounts, a first audit with no structure at all found tracking issues that are very hard to catch by hand. I tell that story in how PPC agencies use AI agents.

A first-read prompt to paste into Claude or ChatGPT

This is what I ask for first on a new account: conversions, then the money. Fill in the account and your target, and paste it as it is. The page is a Claude artifact, so in ChatGPT ask for a table in the chat instead. Google's server only reads, so on its own Claude stops at the page and changes nothing. Below is Claude's answer on a sample store's account, in the setup we build for clients, where Claude also makes the changes once you say yes.

The prompt
Read this Google Ads account before we change anything in it.

Account: <account name or ID>
My target: <the ROAS or CPA your margins allow, such as 400% ROAS>
Period: the last 30 days, ending 3 days ago, since Google's reporting can lag up to 2 days.

1. Conversions first: which actions count in the Conversions column and what each one counts. Flag anything counted twice, a step before the sale or lead counted as a conversion, and a primary action that recorded nothing.
2. Then the money: each campaign by cost, with spend, conversions, conversion value and ROAS or CPA against my target. If something is counted twice, show each campaign on the corrected count too.
3. What I should do, most urgent first, each with its evidence. A tracking fix goes first, with what would confirm which count is right. On the day of the fix, move each campaign's target by the same percentage as its ROAS or CPA moves on the corrected count, never past my target, then leave targets and budgets alone for 1 to 2 conversion cycles.
4. What you couldn't check, and what you'd need from outside Google Ads.

Keep it short, use the words from the Google Ads interface, keep tables to 5 columns, and check every sum.
Show it as one page (an artifact), with an Approve and a Reject on each change.
Change nothing until I say yes. When I say yes, make the changes and check them in the account.
Example
Read this Google Ads account before we change anything in it. …

Purchase and GA4 (web) purchase are both primary, so most sales count twice in the Conversions column: 879.71 conversions and 1,080% ROAS for 17 Sep to 16 Oct. On one purchase action the account is at 613% (Purchase) or 467% (GA4), both over your 400%, but on the GA4 count PMax and Generic fall under it. Add to cart is secondary and stays out, and no primary action is empty.

Account readclaude.ai/code/artifact/9a2629d6…

claude.ai/code/artifact/9a2629d6-8817-76d2-aeed-f96b1967c5f9
Google Ads · conversions and ROAS · last 30 days

Two purchase actions count the same sales: 1,080% ROAS is 467% to 613% on one count

Sample Furniture Store · 3 campaigns · 17 Sep to 16 Oct 2026

Cost€41,119.143 campaigns, 17 Sep to 16 Oct
ROAS as reported1,080%Both purchase actions, 879.71 conversions
ROAS, Purchase only613%€252,084.95 from 493.62 conversions
ROAS, GA4 only467%€192,129.07 from 386.09 conversions

Conversions

All three are set to Count: Every. Purchase and GA4 (web) purchase are both primary, so most sales count twice; Add to cart is secondary and stays out; no primary action is empty.

Conversion actionGoalAction optimizationConversionsConv. value
PurchasePurchasesPrimary493.62€252,084.95
Sample Furniture Store - GA4 (web) purchasePurchasesPrimary386.09€192,129.07
Add to cartAdd to cartSecondary0.00 (2,870.56 in All conv.)€0.00
Conversions column879.71€444,214.02

Campaigns by cost

As reported, then on one purchase action. On Purchase only all three clear your 400%; on GA4 only, PMax and Generic fall under it.

CampaignCostConversionsConv. valueROAS, as reported
NL | PMax | All products€23,412.18431.02€208,546.84891%
NL | Search | Generic€13,193.64201.95€109,123.17827%
NL | Search | Brand€4,513.32246.74€126,544.012,804%
Total€41,119.14879.71€444,214.021,080%
CampaignConversions, Purchase onlyConv. value, Purchase onlyROAS, Purchase onlyROAS, GA4 only
NL | PMax | All products242.92€118,860.76508%383%
NL | Search | Generic113.24€61,964.93470%357%
NL | Search | Brand137.46€71,259.261,579%1,225%
Total493.62€252,084.95613%467%

What to do

Most urgent first. The fix and both targets on the same day, then no target or budget change for 1 to 2 conversion cycles.

Fix€192,129.07 of conv. value in 30 days

Set GA4 (web) purchase to secondary

NowPurchase and GA4 (web) purchase both primary
AfterPurchase primary, GA4 (web) purchase secondary
Evidence
Both are primary purchase actions and both record sales in all 3 campaigns, at €510.69 and €497.63 per conversion.
Why Purchase
It is Google Ads' own tag …; GA4 (web) purchase stays in All conv. to compare.
Confirms it
The store's orders from Google Ads clicks for 17 Sep to 16 Oct, against 493.62 for Purchase and 386.09 for GA4; if they sit nearer 386.09, I swap the two.
Same day€23,412.18 in 30 days

PMax: lower the target ROAS by the same 43.0%

NowTarget ROAS 800%
AfterTarget ROAS 456%
Why
Its ROAS goes from 891% to 508% on Purchase only, down 43.0%; left at 800%, the target would cut its bids.
If GA4 is kept
400%, your target: the same move would give 344%.
Same day€4,513.32 in 30 days

Brand: lower the target ROAS by the same 43.7%

NowTarget ROAS 2,500%
AfterTarget ROAS 1,408%
Why
Its ROAS goes from 2,804% to 1,579% on Purchase only, down 43.7%.
If GA4 is kept
1,092%.
Watch€13,193.64 in 30 days

Generic: no target to move, budget only after the hold

Evidence
Maximize conversion value with no target ROAS …
Later
More budget only if Purchase is the right count: 470% on it, 357% on GA4 only.

What I couldn't check

  • Which count is right: needs the store's orders, revenue and returns from Google Ads clicks for 17 Sep to 16 Oct.
  • Whether the Purchase tag sends the transaction ID, so a reloaded thank-you page isn't counted again: needs the site or Tag Manager.
  • How long a conversion cycle is here: Days to conversion wasn't part of this read, and it sets how long the hold runs.
  • Why PMax shows 270.55 Purchase in All conv. but 242.92 in Conversions: this read doesn't show what the other 27.63 are.

I changed nothing in the account.

Want me to set GA4 (web) purchase to secondary and move PMax to 456% and Brand to 1,408% target ROAS today?

I checked the store's orders and they match the Purchase count. Go ahead with all three today.

Done. Google checked all three changes before they were made, and when I read them back from the account, each one matched:

Where Change Was Now
Sample Furniture Store - GA4 (web) purchase Action optimization Primary Secondary
NL | PMax | All products Target ROAS 800% 456%
NL | Search | Brand Target ROAS 2,500% 1,408%

Purchase is now the only primary action, so the Conversions column counts each sale once. Next, targets and budgets stay as they are for 1 to 2 conversion cycles, and I'll read Days to conversion to find out how long that is. …

Reply to Claude…
The prompt above, answered by Claude on a sample furniture store's account. Example numbers.

What it can't do, and how to keep the account safe

Google built this version to read only. Google's guide says it "cannot modify bids, pause campaigns, or create new assets". That leaves out a few things.

  • No changes. It can't change bids or budgets, pause anything, or add ads, keywords or negatives.
  • Only Google Ads. It can't see GA4, your CRM or your store. So it knows what Google Ads counted as a sale, but not if the sale happened.
  • Some data stays out. Google's API doesn't give it Auction Insights. The change history it reads only goes back 30 days and can miss changes you see in the interface. Low-volume search terms stay hidden, like in Google Ads.
  • It only answers when you ask. For a check every morning, you need something that asks for you on a schedule.

The server is read-only, but your login isn't. When you sign in, the app gets everything your Google Ads user can do, because Google has no read-only option for apps. So I keep the sign-in as safe as a password. If you just want it to read, sign in with a Google Ads user that has Read-only access, which Google's roles say can't edit campaigns.

How to make changes, add GA4 and run daily checks

For changes, we add our own connection next to Google's server. It works through Google's API, and it's what we set up for clients.

You want to Use this
Let Claude make the changes What we set up for clients. Claude asks, you say yes, and it makes the change and checks it.
Read GA4 next to Google Ads Google's Google Analytics MCP server, which is still experimental. It can only read too.
Check every account each morning A setup that asks the same questions on a schedule, the way agencies run it.

In that setup, Claude has Google test each change first and makes it only after your yes. It also logs what each change replaced, so any of it can be put back.

Without a setup like this, you make the changes yourself or import them into Google Ads Editor.

How to connect it to Claude or ChatGPT on your computer

You set it up once, and it runs on your computer with your own Google access. The server and Google's API cost nothing.

1. Install pipx. It runs the server for you, and it needs Python 3.10 or newer. On a Mac with Homebrew, run this in the Terminal, then open a new Terminal window.

brew install pipx
pipx ensurepath

On Windows, install Python 3.10 or newer from python.org. Then run this in the Command Prompt, and open a new one.

py -m pip install --user pipx
py -m pipx ensurepath

2. Turn on the Google Ads API. Open the Google Ads API in the Google Cloud console, create a project when it asks and click Enable. Open the project picker at the top and copy the project ID, not the name. For now the project only works with test accounts.

3. Apply for Explorer access. On the Google Ads API Overview page, expand Upgrade access level, check that the next level says Explorer, and click Apply for access. Most projects get it automatically, and it gives you up to 2,880 operations a day on real accounts. If you're turned down, check billing, because Google can reject a project on the free trial. Upgrade it to a paid account and apply again. If an older project that used the API before 9 September gets an authorization error on real accounts, Google says to apply in a new project.

4. Set up the sign-in screen. In the console menu, open Google Auth Platform, then Branding, and click Get started. Give the app a name and your email. For Audience, pick Internal if your Google account is on Google Workspace and the project is in your organization. Otherwise pick External. Add your email as the contact, agree to the policy and click Create. With External, open Audience and add your email under Test users.

5. Create the OAuth client. In Google Auth Platform, open Clients and click Create client. Choose Desktop app as the type, then click Create. Download the JSON file right away, because Google shows the secret only once.

6. Sign in once. Install the Google Cloud CLI from Google's install page. Then run this line in the Terminal, with the path to your JSON file at the end.

gcloud auth application-default login --scopes https://www.googleapis.com/auth/adwords,https://www.googleapis.com/auth/cloud-platform --client-id-file=/Users/yourname/Documents/client_secret.json

Sign in with the Google account that opens your Google Ads accounts. If Google warns that the app isn't verified, that's normal for your own app, so continue and allow access. Then copy the path the Terminal prints after "Credentials saved to file". On Windows the file is in %APPDATA%\gcloud, and you write its path with forward slashes in the blocks below. With External in Testing, Google ends the sign-in after 7 days, so run the line again when the server stops answering.

7. Add the server to your AI app. Each block needs your manager account's ID without dashes, the path from step 6 and your project ID. If you don't use a manager account, delete the manager line, or the first -e part of the Claude Code line. I'd pin the version, so the server doesn't change on you. The blocks run 0.0.5, the newest version, released on 9 October 2026.

For Claude Desktop, first run which pipx in the Terminal (where pipx on Windows). Put the full path it prints in place of "pipx" in the block, because Claude Desktop often can't find pipx by name. Then open the Claude menu, then Settings, Developer and Edit Config. Paste the block into that file (inside its mcpServers, if it already has some), save it, quit Claude completely and open it again.

{
  "mcpServers": {
    "google-ads-mcp": {
      "command": "pipx",
      "args": ["run", "--spec", "google-ads-mcp==0.0.5", "google-ads-mcp"],
      "env": {
        "GOOGLE_ADS_LOGIN_CUSTOMER_ID": "1234567890",
        "GOOGLE_APPLICATION_CREDENTIALS": "/Users/yourname/.config/gcloud/application_default_credentials.json",
        "GOOGLE_PROJECT_ID": "your-project-id"
      }
    }
  }
}

For Claude Code, run this line. The --scope user part makes it work in all your projects.

claude mcp add google-ads-mcp --scope user -e GOOGLE_ADS_LOGIN_CUSTOMER_ID=1234567890 -e GOOGLE_APPLICATION_CREDENTIALS=/Users/yourname/.config/gcloud/application_default_credentials.json -e GOOGLE_PROJECT_ID=your-project-id -- pipx run --spec google-ads-mcp==0.0.5 google-ads-mcp

For Codex and the ChatGPT desktop app, which share one setup, add this to config.toml in the .codex folder of your user folder. If the server doesn't show up, restart the app. The 60 seconds give the first start time to download the server.

[mcp_servers.google_ads]
command = "pipx"
args = ["run", "--spec", "google-ads-mcp==0.0.5", "google-ads-mcp"]
startup_timeout_sec = 60

[mcp_servers.google_ads.env]
GOOGLE_ADS_LOGIN_CUSTOMER_ID = "1234567890"
GOOGLE_APPLICATION_CREDENTIALS = "/Users/yourname/.config/gcloud/application_default_credentials.json"
GOOGLE_PROJECT_ID = "your-project-id"

8. Test it. Ask "What customers do I have access to?", then ask for last week's cost in one account, by its ID. If it matches what you see in Google Ads, it works.

How to connect it to Claude or ChatGPT in the browser

Claude and ChatGPT in the browser can't reach a server on your computer. They connect from their own cloud, so the server has to be online. Google's way is to put it on Cloud Run in your own project. If you're not technical, I'd leave this part to a developer.

  1. In Google Auth Platform, create another OAuth client, this time a Web application. Add these two under Authorized redirect URIs, the first for Claude and the second for ChatGPT. Then copy the client ID and secret.
https://claude.ai/api/mcp/auth_callback
https://chatgpt.com/connector_platform_oauth_redirect
  1. Under Data Access, add the Google Ads scope, and under Audience, add everyone who will connect as a test user.
  2. Then run these lines in the terminal, with your own values. Delete the manager ID if you don't have one. The last line is for after the first deploy, with the address Cloud Run gives you.
git clone https://github.com/googleads/google-ads-mcp.git
cd google-ads-mcp
gcloud config set project YOUR_PROJECT_ID
gcloud artifacts repositories create mcp-servers --repository-format=docker --location=us-central1
gcloud builds submit --tag us-central1-docker.pkg.dev/YOUR_PROJECT_ID/mcp-servers/google-ads-mcp:latest .
gcloud run deploy google-ads-mcp --image us-central1-docker.pkg.dev/YOUR_PROJECT_ID/mcp-servers/google-ads-mcp:latest --platform managed --region us-central1 --allow-unauthenticated --set-env-vars="GOOGLE_PROJECT_ID=YOUR_PROJECT_ID,GOOGLE_ADS_MCP_OAUTH_CLIENT_ID=YOUR_CLIENT_ID,GOOGLE_ADS_MCP_OAUTH_CLIENT_SECRET=YOUR_CLIENT_SECRET,GOOGLE_ADS_LOGIN_CUSTOMER_ID=1234567890,FASTMCP_HOST=0.0.0.0"
gcloud run services update google-ads-mcp --region us-central1 --update-env-vars="GOOGLE_ADS_MCP_BASE_URL=https://your-cloud-run-url.a.run.app"
  1. In Claude or ChatGPT, add a custom connector with that address plus /mcp, pick OAuth and paste your client ID and secret.

Never deploy it without the OAuth client. Google warns that without it, anyone with the address can use the server's own Google access. For ChatGPT there's one more way, OpenAI's Secure MCP Tunnel, which reaches the server on your computer without putting it online.

Before you connect client accounts, make sure their data only goes through business plans, such as Claude Team or ChatGPT Business. Google's rules on hosted servers are in the API access article.

Companies are opening their tools to AI through MCPs, and Google opened the reading first. I think that's the right order, because reading changes nothing in the account. The next step is to run this check on every account, every morning.

Questions people ask

Is the Google Ads MCP server read-only?

Yes. Google's guide says it can't modify bids, pause campaigns or create new assets. The Google login behind it can still edit the account through other tools, so keep it as safe as a password, or connect it with a Read-only Google Ads user, which can't edit campaigns.

Is the Google Ads MCP server free?

Yes. The server is open source, and Google charges nothing for the Google Ads API. You pay for your AI plan, and for hosting if you put the server online.

Do I need a developer token for the Google Ads MCP server?

No. Google retired developer tokens on 9 September 2026. Access now comes from the Google Cloud project where you create the app's sign-in, and that project needs Explorer access or above to read real accounts.

How do I connect the Google Ads MCP server to Claude or ChatGPT?

Turn on the Google Ads API in a Google Cloud project, apply for Explorer access, create an OAuth client for a desktop app and sign in with Google's gcloud command. Then add the server's block to Claude Desktop, run one command in Claude Code, or add the same settings to Codex and the ChatGPT desktop app. Claude and ChatGPT in the browser need the server hosted online, or for ChatGPT, OpenAI's secure tunnel.

Can AI make changes in Google Ads?

Not through this server, because the current version only reads. In the setup we build for clients, Claude prepares each change and asks you first. Once you say yes, it makes the change, checks it in the account and logs what was there before.

See which growth engines fit your company.

On the call we look at your business and your channels, and show you which engines we would build first.