Adloop MCP Server

The AI command center for Google Ads, GA4, and tracking code.

Remote serverstreamable-httpPython

What is the Adloop MCP server?

The AI command center for Google Ads, GA4, and tracking code. Exposed over MCP by the adloop mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

An MCP server that gives your AI assistant read + write access to Google Ads and GA4 — with safety guardrails that prevent accidental spend.

Its toolset

Everything the assistant can do here goes through one of these:

  • get_account_summaries — List GA4 accounts and properties
  • run_ga4_report — Custom reports — sessions, users, conversions, page performance
  • run_realtime_report — Live data — verify tracking fires after deploys
  • get_tracking_events — All configured events and their volume
  • list_accounts — Discover accessible Ads accounts
  • get_campaign_performance — Campaign metrics — impressions, clicks, cost, conversions, CPA
  • get_ad_performance — Ad copy analysis — headlines, descriptions, CTR
  • get_keyword_performance — Keywords — quality scores, competitive metrics
  • get_search_terms — What users actually searched before clicking
  • get_negative_keywords — List direct campaign-level negative keywords
  • get_negative_keyword_lists — List all shared negative keyword lists (SharedSets) — names, IDs, status, keyword count
  • get_negative_keyword_list_keywords — List the keywords inside a specific shared negative keyword list

Configuration

  • Python 3.11+ - A Google Ads account with an MCC (Manager Account) - A Google Ads Developer Token (see below)

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Adloop's toolset — get_account_summaries, run_ga4_report, run_realtime_report and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Daniel Klose; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Adloop's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Adloop.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the adloop mcp server does with a few real requests.

Available tools

ToolWhat it does
get_account_summariesList GA4 accounts and properties
run_ga4_reportCustom reports — sessions, users, conversions, page performance
run_realtime_reportLive data — verify tracking fires after deploys
get_tracking_eventsAll configured events and their volume
list_accountsDiscover accessible Ads accounts
get_campaign_performanceCampaign metrics — impressions, clicks, cost, conversions, CPA
get_ad_performanceAd copy analysis — headlines, descriptions, CTR
get_keyword_performanceKeywords — quality scores, competitive metrics
get_search_termsWhat users actually searched before clicking
get_negative_keywordsList direct campaign-level negative keywords
get_negative_keyword_listsList all shared negative keyword lists (SharedSets) — names, IDs, status, keyword count
get_negative_keyword_list_keywordsList the keywords inside a specific shared negative keyword list
get_negative_keyword_list_campaignsList which campaigns a shared negative keyword list is attached to
get_recommendationsGoogle's auto-generated recommendations with type, estimated impact, and campaign context

How to install the Adloop MCP server

{
  "mcpServers": {
    "adloop": {
      "command": "uvx",
      "args": ["adloop"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.11+ - A Google Ads account with an MCC (Manager Account) - A Google Ads Developer Token (see below)

Example prompts to try

  • Use Adloop to get account summaries.
  • Use Adloop to run ga4 report.
  • Use Adloop to run realtime report.

Frequently asked questions

It connects Adloop to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (get_account_summaries, run_ga4_report, run_realtime_report, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Adloop directly.