A read-only Model Context Protocol (MCP) server for Google Ads (via GAQL), Search Console, and Google Analytics 4. Designed for AI assistants and LLM agents to safely read campaign performance, search analytics, website traffic, and more.

If search targets a manager (MCC) account and finds no data directly, it automatically:

1. Detects the account is a manager
2. Finds child accounts
3. Runs the query on each child
4. Returns combined results with _source_customer_id marking which account each row belongs to

• A Google Ads developer token (apply via Google Ads API Center)
• Google Cloud service account with the following APIs enabled:
  • Google Ads API
  • Search Console API
  • Google Analytics Data API
  • Google Analytics Admin API

git clone https://github.com/ceotind/open-google-mcp.git
cd open-google-mcp

A single service account authenticates Google Ads, Search Console, and Google Analytics 4.

1. Go to GCP Console → APIs & Services → Credentials → Create Credentials → Service Account
2. Download the JSON key file, then copy these fields into .env:
   • GOOGLE_SERVICE_ACCOUNT_EMAIL
   • GOOGLE_SERVICE_ACCOUNT_KEY (the private_key — keep the \n escapes)
   • GOOGLE_SERVICE_ACCOUNT_KEY_ID
   • GOOGLE_SERVICE_ACCOUNT_CLIENT_ID
   • GOOGLE_SERVICE_ACCOUNT_PROJECT_ID
3. Google Ads: add the service account email in your manager account (Settings → Account access → Service account users)
4. Search Console: add the same email to your property (Settings → Users and permissions → Add user, grant Full access)
5. Google Analytics 4: add the same email to your GA4 property (Admin → Account Access Management → Add user → Viewer)

cp .env.example .env
# Edit .env with the service account values + developer token

docker compose build
docker compose run --rm open-google-mcp

Claude Desktop:

{
  "mcpServers": {
    "open-google-mcp": {
      "command": "docker",
      "args": ["compose", "run", "--rm", "open-google-mcp"],
      "workdir": "/path/to/open-google-mcp"
    }
  }
}

opencode:

{
  "mcp": {
    "open-google-mcp": {
      "type": "local",
      "command": ["docker", "compose", "run", "--rm", "open-google-mcp"],
      "workdir": "/path/to/open-google-mcp",
      "enabled": true
    }
  }
}

Cursor:

• Name: open-google-mcp
• Type: command
• Command: docker compose run --rm open-google-mcp
• Working directory: /path/to/open-google-mcp

git clone https://github.com/ceotind/open-google-mcp.git
cd open-google-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

Same steps as Option A above — a single service account works for Ads, GSC, and GA4.

1. Go to GCP Console → APIs & Services → Credentials → Create Credentials → Service Account
2. Download the JSON key file, then copy these fields into .env:
   • GOOGLE_SERVICE_ACCOUNT_EMAIL
   • GOOGLE_SERVICE_ACCOUNT_KEY
   • GOOGLE_SERVICE_ACCOUNT_KEY_ID
   • GOOGLE_SERVICE_ACCOUNT_CLIENT_ID
   • GOOGLE_SERVICE_ACCOUNT_PROJECT_ID
3. Google Ads: add the service account email in your manager account
4. Search Console: add the same email to your property with Full access
5. Google Analytics 4: add the same email to your GA4 property with Viewer access

cp .env.example .env

source .venv/bin/activate
source .env
python -m open_google_mcp

Or use the wrapper script (loads .env automatically):

./server.sh

Claude Desktop:

{
  "mcpServers": {
    "open-google-mcp": {
      "command": "/path/to/open-google-mcp/server.sh"
    }
  }
}

opencode:

{
  "mcp": {
    "open-google-mcp": {
      "type": "local",
      "command": ["/path/to/open-google-mcp/server.sh"],
      "enabled": true
    }
  }
}

Cursor:

• Name: open-google-mcp
• Type: command
• Command: /path/to/open-google-mcp/server.sh

list_accessible_customers

get_resource_metadata(resource_name="campaign")

search(
  customer_id="1234567890",
  resource="campaign",
  fields=["campaign.id", "campaign.name", "campaign.status",
          "campaign.advertising_channel_type", "metrics.clicks",
          "metrics.impressions", "metrics.cost_micros"],
  conditions=["campaign.status = 'ENABLED'",
              "segments.date DURING LAST_30_DAYS"],
  orderings=["metrics.clicks DESC"],
  limit=10
)

search(
  customer_id="1234567890",
  resource="customer_client",
  fields=["customer_client.id", "customer_client.descriptive_name", "customer_client.manager"]
)

gsc_list_properties

gsc_get_search_analytics(
  site_url="https://example.com",
  days=28,
  dimensions="query",
  row_limit=10
)

gsc_get_performance_overview(
  site_url="https://example.com",
  days=28
)

gsc_compare_search_periods(
  site_url="https://example.com",
  period1_start="2025-01-01",
  period1_end="2025-01-31",
  period2_start="2025-02-01",
  period2_end="2025-02-28",
  dimensions="query",
  limit=10
)

gsc_get_advanced_search_analytics(
  site_url="https://example.com",
  dimensions="query,device",
  search_type="WEB",
  row_limit=50,
  sort_by="impressions",
  sort_direction="descending",
  filters='[{"dimension":"country","operator":"equals","expression":"usa"}]'
)

gsc_inspect_url(
  site_url="https://example.com",
  page_url="https://example.com/blog/post"
)

gsc_get_sitemaps(site_url="https://example.com")

ga4_list_properties

Returns your property ID (e.g. 123456789) — use it in all other GA4 tools.

ga4_get_metadata(property_id="123456789")

Returns 300+ dimensions and 100+ metrics available for reporting.

ga4_run_report(
  property_id="123456789",
  metrics="activeUsers,sessions,newUsers",
  start_date="28daysAgo",
  end_date="today"
)

ga4_run_report(
  property_id="123456789",
  dimensions="country",
  metrics="activeUsers",
  start_date="28daysAgo",
  end_date="today",
  limit=10,
  order_bys=[{"metric": "activeUsers", "desc": true}]
)

ga4_run_report(
  property_id="123456789",
  dimensions="pagePath",
  metrics="screenPageViews,activeUsers",
  start_date="28daysAgo",
  end_date="today",
  limit=10,
  order_bys=[{"metric": "screenPageViews", "desc": true}]
)

ga4_run_report(
  property_id="123456789",
  dimensions="sessionDefaultChannelGrouping",
  metrics="activeUsers,sessions",
  start_date="28daysAgo",
  end_date="today",
  limit=10,
  order_bys=[{"metric": "activeUsers", "desc": true}]
)

ga4_run_report(
  property_id="123456789",
  dimensions="city",
  metrics="activeUsers",
  start_date="28daysAgo",
  end_date="today",
  filters={"field": "country", "type": "string_filter",
           "value": "Ireland", "match_type": "EXACT"},
  limit=10
)

ga4_run_report(
  property_id="123456789",
  dimensions="deviceCategory",
  metrics="activeUsers,sessions",
  start_date="28daysAgo",
  end_date="today"
)

ga4_run_realtime_report(
  property_id="123456789",
  dimensions="country,deviceCategory",
  metrics="activeUsers",
  limit=10
)

You can use relative or absolute dates:

• Relative: today, yesterday, 7daysAgo, 28daysAgo, 30daysAgo
• Absolute: 2026-01-01 (YYYY-MM-DD format)

• Field names must be fully qualified: campaign.id, not id
• Date format: YYYY-MM-DD with dashes
• Relative dates: DURING LAST_7_DAYS, LAST_30_DAYS, THIS_MONTH, THIS_QUARTER
• For change_event resource, limit must be ≤ 10000
• Conditions are AND-combined
• Use get_resource_metadata first to discover valid fields

MIT