About google-ads-manager-mcp
A local MCP server for Google Ads users who need reporting and controlled campaign management. It supports read and write operations, with every change previewed and explicitly confirmed before execution.
Key features
- 01Run GAQL reports
- 02Inspect campaigns, ad groups, keywords, and search terms
- 03Create and update campaign assets
- 04Preview writes before confirmation
- 05Confirm or reject pending changes
Use cases
- 01Review campaign performance and triggered search terms
- 02Draft campaign, budget, ad group, or ad changes
- 03Pause or enable campaigns and keywords
MCP support
Exposes Google Ads reporting and management tools to MCP clients. Write operations return a draft for preview and require `confirm_write` before changing the account.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y google-ads-manager-mcpGOOGLE_ADS_CLIENT_IDOAuth client ID from a Google Cloud 'Desktop app' credentialGOOGLE_ADS_CLIENT_SECRETSecretOAuth client secret from the same Google Cloud credentialGOOGLE_ADS_DEVELOPER_TOKENSecretDeveloper token from Google Ads > Tools & Settings > API CenterGOOGLE_ADS_REFRESH_TOKENSecretOAuth refresh token, generated by running `npm run auth`GOOGLE_ADS_CUSTOMER_IDThe Google Ads account this server manages (10-digit ID, dashes optional)GOOGLE_ADS_LOGIN_CUSTOMER_IDManager (MCC) account ID, only needed if GOOGLE_ADS_CUSTOMER_ID is a client account under a manager accountLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
16Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEGoogle Ads Manager MCP
Unofficial, community-maintained project. Not affiliated with, endorsed by, or sponsored by Google. "Google Ads" is a trademark of Google LLC.
A local MCP (Model Context Protocol) server that lets an AI assistant read and manage a Google Ads account: run GAQL reports, create campaigns, pause/enable campaigns, and add keywords.
Google also publishes an official Google Ads MCP server, which is read-only (reporting/diagnostics only). This project covers the same reporting ground and adds write support — creating and editing campaigns, budgets, ad groups, keywords, and ads — gated behind a draft/confirm safety layer so nothing changes in your account by accident.
Every write goes through a draft → confirm safety flow: the tool that "creates" or "updates"
something only validates the change against Google's API (validate_only) and hands back a
draftId with a preview. Nothing changes in your Ads account until you call confirm_write with
that draftId. Drafts expire after 10 minutes.
Tools
Read-only:
list_accessible_customers— which accounts this refresh token can reachsearch_gaql— run any raw GAQLSELECTqueryget_campaigns— campaigns with status, budget, and core metricsget_ad_groups— ad groups (optionally filtered to a campaign) with metricsget_keywords— keyword criteria with match type, status, and metricsget_search_terms— actual search terms that triggered your ads, for finding negative keyword candidates
Write (draft → confirm):
create_campaign— new campaign + budget, createdPAUSEDunless you say otherwiseupdate_campaign_status— enable / pause / remove a campaignupdate_campaign_budget— change an existing campaign's daily budgetadd_keywords— add keyword criteria to an ad groupcreate_ad_group— new ad group inside an existing campaignupdate_ad_group_status— enable / pause / remove an ad groupupdate_keyword_status— enable / pause / remove a keyword criterionadd_negative_keywords— add negative keyword criteria to an ad groupcreate_responsive_search_ad— new responsive search ad, createdPAUSEDunless you say otherwiseconfirm_write— execute a previously returneddraftIdfor real
Setup
1. Google Ads developer token
Google Ads → Tools & Settings → API Center. Test-account tokens are issued instantly; a production-level token requires Google's manual review (roughly 1-2 weeks), so apply for that early if you'll use this beyond a test account.
2. OAuth client
Google Cloud Console → APIs & Services → Credentials → Create credentials → OAuth client ID. Choose application type Desktop app. Copy the client ID and client secret.
3. Configure environment
cp .env.example .env
Fill in GOOGLE_ADS_CLIENT_ID, GOOGLE_ADS_CLIENT_SECRET, GOOGLE_ADS_DEVELOPER_TOKEN, and
GOOGLE_ADS_CUSTOMER_ID (the account this server should manage — 10 digits, dashes optional). If
that account is a client under a manager (MCC) account, also set GOOGLE_ADS_LOGIN_CUSTOMER_ID to
the manager account's ID.
4. Get a refresh token
npm install
npm run auth
This opens an authorization URL — open it, sign in with the Google account that has access to
your Ads account, approve the adwords scope. The script prints a GOOGLE_ADS_REFRESH_TOKEN;
add it to .env.
5. Build
npm run build
6. Point your MCP client at it
For Claude Desktop / Claude Code, add to your MCP config:
{
"mcpServers": {
"google-ads-manager": {
"command": "node",
"args": ["/absolute/path/to/google ads manger mcp/build/index.js"],
"env": {
"GOOGLE_ADS_CLIENT_ID": "...",
"GOOGLE_ADS_CLIENT_SECRET": "...",
"GOOGLE_ADS_DEVELOPER_TOKEN": "...",
"GOOGLE_ADS_REFRESH_TOKEN": "...",
"GOOGLE_ADS_CUSTOMER_ID": "..."
}
}
}
}
(Or skip the env block and just make sure .env is populated — the server loads it via
dotenv when run directly, e.g. npm run dev during local iteration.)
Notes
- This is scoped to a single Google Ads account (
GOOGLE_ADS_CUSTOMER_ID). To manage several client accounts under one manager account, either run one instance per customer ID, or extendgoogleAdsClient.tsto accept acustomerIdargument per tool call. - New campaigns default to
PAUSED(startEnabled: false) so nothing spends until you explicitly enable it.
Contributing
Issues and PRs welcome — new report types, negative-keyword-at-campaign-level support, and multi-account (MCC) handling are the most useful next additions.
License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.