google-ads-manager-mcp

google-ads-manager-mcp

MCP server to read and manage Google Ads accounts via GAQL queries, campaign/ad group/keyword operations, and safe write support with draft-confirm flow.

Category
Visit Server

README

Google 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 reach
  • search_gaql — run any raw GAQL SELECT query
  • get_campaigns — campaigns with status, budget, and core metrics
  • get_ad_groups — ad groups (optionally filtered to a campaign) with metrics
  • get_keywords — keyword criteria with match type, status, and metrics
  • get_search_terms — actual search terms that triggered your ads, for finding negative keyword candidates

Write (draft → confirm):

  • create_campaign — new campaign + budget, created PAUSED unless you say otherwise
  • update_campaign_status — enable / pause / remove a campaign
  • update_campaign_budget — change an existing campaign's daily budget
  • add_keywords — add keyword criteria to an ad group
  • create_ad_group — new ad group inside an existing campaign
  • update_ad_group_status — enable / pause / remove an ad group
  • update_keyword_status — enable / pause / remove a keyword criterion
  • add_negative_keywords — add negative keyword criteria to an ad group
  • create_responsive_search_ad — new responsive search ad, created PAUSED unless you say otherwise
  • confirm_write — execute a previously returned draftId for 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 extend googleAdsClient.ts to accept a customerId argument 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

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured