mcp-google-ads MCP — Use Cases, Install & Live Demo

Why use it

Key features

GAQL passthrough — full query power, not just pre-baked reports
OAuth (for individuals) or Service Account (for automation)
Campaign, ad group, ad, and keyword metrics
Impressions, clicks, conversions, cost, CTR, avg CPC
Python 3.11+; .env-based config

Live Demo

What it looks like in practice

google-ads.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "google-ads": {
      "command": "uvx",
      "args": [
        "mcp-google-ads"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "google-ads": {
      "command": "uvx",
      "args": [
        "mcp-google-ads"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "google-ads": {
      "command": "uvx",
      "args": [
        "mcp-google-ads"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "google-ads": {
      "command": "uvx",
      "args": [
        "mcp-google-ads"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "google-ads",
      "command": "uvx",
      "args": [
        "mcp-google-ads"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "google-ads": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-google-ads"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add google-ads -- uvx mcp-google-ads

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use mcp-google-ads

Weekly campaign health check across accounts

👤 Paid marketing managers, agencies ⏱ ~20 min intermediate

When to use: Weekly — which campaigns are burning budget with poor CTR / high CPA?

Prerequisites

Google Ads Developer Token (approved) — ads.google.com > Tools > API Center — 1-3 business days
OAuth client OR service account with Ads access — Google Cloud Console

Flow

List accounts

List all Google Ads accounts I can access.✓ Copied

→ MCC + child accounts
Pull performance

For each account, pull last 7 days: campaign name, cost, clicks, conversions, CPA. Flag campaigns where CPA > $100.✓ Copied

→ Ranked hot-spot list
Propose action

For the worst 3 campaigns, suggest: pause, lower bid, or investigate further based on the numbers.✓ Copied

→ Action plan

Outcome: Weekly hotspot review in minutes.

Pitfalls

Attribution windows differ by conversion action — Include segments.conversion_action_name and check each separately

Combine with: notion

Mine search terms for negative keywords

👤 Performance marketers ⏱ ~15 min intermediate

When to use: Regular account hygiene — catch wasteful queries before they add up.

Flow

Pull search terms

GAQL: search_term_view for last 30 days, columns [search_term, campaign, cost, conversions]. Cost > $10 and conversions = 0.✓ Copied

→ Wasteful query list
Group and recommend

Group by recurring phrases. Suggest negative keywords to add at account or campaign level.✓ Copied

→ Negative list with level

Outcome: A tidy negative-keyword list to apply.

Pitfalls

Broad-matching negatives can block legit traffic — Use exact or phrase negatives first; broad only when very confident

Audit ad copy performance across a campaign

👤 Copywriters, PPC leads ⏱ ~15 min intermediate

When to use: You launched 3 responsive ads and want to know which combos perform.

Flow

Pull ad stats

For campaign X, list all ads + their 30-day CTR + conv rate. Sort by conv rate desc.✓ Copied

→ Ad performance ranked
Recommend

What patterns distinguish top-performing ad copy? What should I iterate on?✓ Copied

→ Copy insights

Outcome: Data-driven creative iteration.

Pitfalls

Low-volume ads look worse than they are due to variance — Require minimum 100 impressions before comparing rates

Combinations

Pair with other MCPs for X10 leverage

google-ads + notion

Weekly marketing digest

Pull last week's Google Ads performance + biggest wins/losses; create a Notion page in 'Marketing Weekly'.✓ Copied

google-ads + postgres

Join Google Ads data with your DB for full-funnel view

Get conversion counts from Google Ads for campaign X. Query the DB for actual closed deals originating from that campaign.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
list_accessible_accounts		Discover the account graph	1 API call
run_gaql	customer_id, query: str	Any custom report	1 API call
campaign_performance	customer_id, date_range	Quick campaign digest	1 API call
ad_performance	customer_id, campaign_id?, date_range	Creative audit	1 API call

Cost & Limits

What this costs to run

API quota: Google Ads API: generous per-day quota; rate-limited per QPS
Tokens per call: Results depend heavily on date range and segments — cap rows
Monetary: API is free; you pay for ads separately
Tip: Always include a date range in GAQL. Running without LIMITs can return 100k rows.

Security

Permissions, secrets, blast radius

Minimum scopes: Read-only on the Ads accounts where possible

Credential storage: Service account JSON or OAuth refresh token — env vars or secret manager

Data egress: Performance data goes to your LLM provider

Never grant: Admin on the Ads account to an agent that does more than read

Developer Token approval has tiers — test tokens have low quota. Apply for production.
Service account must be added as a user in Ads MCC with appropriate role.

Troubleshooting

Common errors and fixes

AUTHENTICATION_ERROR or PERMISSION_DENIED

Service account email not added to MCC with access, or developer_token wrong. Check ads.google.com > Access & Security.

Too many metrics for segment

GAQL has restrictions on which metrics can be combined with which segments. Query a simpler subset.

Verify: Read the GAQL compatibility table

Test token quota exceeded

Apply for production token; until then, test on small accounts with low query frequency.

Alternatives

mcp-google-ads vs others

Alternative	When to use it instead	Tradeoff
Google Ads UI / Editor	You only occasionally pull reports	Manual; no LLM insight
Meta Ads MCP	You also run Meta ads	Different platform; own auth

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills