Google Ads MCP Admin
Provides tools for administering Google Ads campaigns, ad groups, budgets, and criteria across manager accounts, with a mutation workflow requiring planning, approval, and verification.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Google Ads MCP AdminPause campaign 8888888888 in account 1234567890"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Google Ads MCP Admin
An extension of Google's official Google Ads MCP that adds confirmed campaign administration across client accounts managed by a Google Ads manager account.
Read tools run directly. Every persistent write requires an immutable plan, a preview, interactive approval, and post-write verification. High-risk changes require two independent approvals.
Safety model
Mutation plans are immutable, expire after 15 minutes, and can be applied only once.
The server revalidates the client hierarchy immediately before a write.
Normal writes require approval for
mutations_apply_mutation_plan.High-risk writes first require
mutations_acknowledge_high_risk_plan, followed by a separate apply approval.Ambiguous API responses are never retried automatically.
Audit records contain metadata and request IDs, not credentials or complete payloads.
Related MCP server: flour-ads
Prerequisites
macOS with the
securityKeychain command available.Python 3.11 or later.
uv.Google Cloud CLI (
gcloud).A Google Cloud project with the Google Ads API enabled.
A Desktop OAuth client authorized for a Google user who can access the target manager account.
An approved Google Ads API developer token.
Install the pinned dependencies:
uv sync --extra devConfigure Codex
Copy the public configuration template and replace its cwd value with the absolute path to this repository:
cp .codex/config.toml.example .codex/config.tomlThe local .codex/config.toml file is ignored by Git. Provide these variables to the Codex process:
export GOOGLE_CLOUD_PROJECT="your-google-cloud-project"
export GOOGLE_ADS_LOGIN_CUSTOMER_ID="1234567890"Google Ads account IDs must contain digits only, without hyphens. GOOGLE_APPLICATION_CREDENTIALS is optional when Application Default Credentials are stored in the standard gcloud location.
You may place non-secret local values in the ignored configuration instead:
[mcp_servers.google_ads_admin.env]
GOOGLE_CLOUD_PROJECT = "your-google-cloud-project"
GOOGLE_ADS_LOGIN_CUSTOMER_ID = "1234567890"Never place the developer token, OAuth client secret, or ADC refresh token in this repository.
Configure OAuth
Create a Desktop OAuth client in Google Auth Platform and download its JSON file outside the repository. Then run:
export GOOGLE_CLOUD_PROJECT="your-google-cloud-project"
scripts/configure-google-ads-oauth.sh "/absolute/path/to/oauth-client.json"The helper enables googleads.googleapis.com and requests only these scopes:
https://www.googleapis.com/auth/adwordshttps://www.googleapis.com/auth/cloud-platform, required for Application Default Credentials
The resulting ADC file is stored outside the repository by gcloud.
Store the developer token
Store the token directly in macOS Keychain. Leaving -w as the final option makes security prompt interactively, so the token does not enter shell history:
security add-generic-password \
-U \
-s codex-google-ads-developer-token \
-a "$USER" \
-wThe launcher reads the token, exports it only to the MCP child process, and never prints it.
Replace the token by repeating the command. Revoke the local Keychain item with:
security delete-generic-password \
-s codex-google-ads-developer-token \
-a "$USER"Start the MCP server
Set the manager account and start the server manually to verify startup:
export GOOGLE_ADS_LOGIN_CUSTOMER_ID="1234567890"
scripts/run-google-ads-mcp.shAfter editing .codex/config.toml:
Restart Codex or reopen the project.
Open
/mcpand confirm thatgoogle_ads_adminis available.Confirm that the official read tools and the five
mutations_*tools are present.
Do not weaken the write approval policies when the server can access production accounts.
Read-only verification
Offline checks require no credentials:
uv run pytest -m "not integration" -qAfter OAuth and Keychain setup, run the opt-in live read test:
export GOOGLE_ADS_DEVELOPER_TOKEN="$(security find-generic-password \
-a "$USER" \
-s codex-google-ads-developer-token \
-w)"
export GOOGLE_ADS_LOGIN_CUSTOMER_ID="1234567890"
GOOGLE_ADS_RUN_INTEGRATION=1 \
uv run pytest tests/integration/test_google_ads_read.py -v
unset GOOGLE_ADS_DEVELOPER_TOKENThe test discovers enabled, non-manager client accounts and queries one of them without writing.
Mutation workflow
Call
mutations_plan_mutationswith a ten-digitcustomer_idand structured operations.Review
preview,old_values,new_values,warnings,risk,plan_id,plan_hash, and expiration.Approve
mutations_apply_mutation_planin Codex for a normal-risk plan.The server revalidates manager access, claims the plan to prevent replay, dispatches it once, and reads the resulting resources.
Review
request_idsandverification.
Use mutations_cancel_mutation_plan with the plan ID and hash to invalidate a pending plan. Plans are held only in memory and disappear when the server restarts.
High-risk changes
The following operations are high risk:
Enabling a campaign.
Creating a budget.
Increasing a budget by more than 25 percent.
Removing ten or more resources in one batch.
First approve mutations_acknowledge_high_risk_plan. Codex then requests a separate approval for mutations_apply_mutation_plan. Neither call can replace or alter the saved operations.
Supported resources
campaign_budgetcampaignad_groupad_group_adad_group_criterion, including keywordscampaign_criterion, including targeting
Supported actions are create, update with an explicit update_mask, and remove. Google Ads removal commonly changes status to REMOVED; it is not physical deletion and may be irreversible.
First persistent write
Complete these checks before any persistent write:
uv run ruff check .uv run pytest -m "not integration" -qThe live read-only integration test.
validate_onlyagainst a dedicated test account:
export GOOGLE_ADS_TEST_CUSTOMER_ID="1234567890"
GOOGLE_ADS_RUN_INTEGRATION=1 \
uv run pytest tests/integration/test_google_ads_validate_only.py -vThe first persistent test should create a PAUSED campaign with the minimum practical budget in a test account. Review and approve its plan, verify the resources, then create and approve a separate removal plan.
If no test account is available, stop after validate_only. A first write to production requires separate explicit authorization and should be limited to one paused resource with minimal financial impact.
Recovery and auditing
Expired or cancelled plan: create a new plan; it cannot be reactivated.
Revoked OAuth grant: rerun
scripts/configure-google-ads-oauth.sh.Replaced developer token: update the Keychain item with
security add-generic-password -U.Ambiguous write response: do not retry; query state once and preserve the returned request ID.
Quota, permission, or policy error: preserve the Google Ads request ID for diagnosis.
Client removed from the manager hierarchy: the pre-write revalidation rejects the operation.
Local audit events are written to audit/google_ads_mcp.jsonl, rotate at 5 MiB, and contain account, plan, resource counts, result, and request IDs. They do not contain complete mutation payloads or credentials.
Development
uv run ruff check .
uv run pytest -m "not integration" -v
uv build
git diff --checkThe official server dependency is pinned to upstream commit f48a6b85e1f43ebd44a72531c9611e2b7265ca28. Review upstream changes, rerun all checks, and inspect MCP tool annotations before updating it.
License
Licensed under the Apache License, Version 2.0. See LICENSE.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityFmaintenanceA read-write MCP server for managing Google Ads campaigns, ad groups, keywords, and ads via natural language.Last updated122The Unlicense
- Alicense-qualityDmaintenanceMCP server for managing ad campaigns across Google Ads, Meta, and more. Enables deploying campaigns, checking performance, and managing budgets from terminal or AI assistants.Last updatedMIT
- AlicenseAqualityAmaintenanceAn MCP server that gives your AI assistant read + write access to Google Ads and GA4 — with safety guardrails that prevent accidental spend.Last updated67223MIT
- Alicense-qualityCmaintenanceA security-first MCP server that enables AI clients to read and write Google Ad Manager data through the Ad Manager API, with least-privilege defaults, gated writes, and per-user OAuth support.Last updated166MIT
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
MCP server for interacting with the Supabase platform
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jomiferse/google-ads-mcp-admin'
If you have feedback or need assistance with the MCP directory API, please join our Discord server