Log inSubmit server
AI Tag Debugger logo

AI Tag Debugger

QA-tests website analytics, advertising, consent, and dataLayer behavior through browser-driven journeys.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install AI Tag Debugger

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "analitikisler-ai-tag-debugger": {
      "command": "npx",
      "args": [
        "-y",
        "@analitikisler/ai-tag-debugger"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

AI Tag Debugger MCP server lets an AI model drive a real browser through website journeys while capturing analytics, advertising, consent, and dataLayer activity. Deterministic checks compare the captured hits with a measurement plan, then a model explains failures in English or Turkish. MCP clients can run audits with their own model, while terminal and CI users can provide an Anthropic, OpenAI, Gemini, OpenAI-compatible, or local Ollama API. Reach for it when releases need repeatable QA for tags, conversions, consent behavior, or campaign attribution.

Use cases

  • Audit checkout conversion tracking before a release
  • Verify consent rejection behavior across advertising tags
  • Compare GA4 and ad-platform purchase values
  • Run measurement-plan checks in CI
  • Trace broken GTM triggers with a container export

Key features

  • Browser-driven journey execution
  • Tracking-hit and dataLayer capture
  • Deterministic measurement-plan checks
  • Consent scenario testing
  • GTM tag and trigger diagnostics
  • MCP and terminal/CI usage

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · @analitikisler/ai-tag-debugger (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads2.7kPackage downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.

How AI Tag Debugger works

What AI Tag Debugger MCP server does

AI Tag Debugger MCP server audits website tracking by replaying user journeys such as browsing a product, adding it to a cart, submitting a lead form, or completing checkout. The browser records tracking requests and dataLayer pushes as the journey runs. Findings are compared with a measurement plan and Consent Mode expectations, then assembled into a human-readable report.

Checks include missing events or parameters, invalid purchase values and currencies, empty purchase items, duplicate hits, cross-platform purchase mismatches, unplanned events, exposed personal data, and missing campaign parameters. Consent checks cover premature advertising requests, missing or late Consent Mode signals, cookies set before consent, and tags that remain active after rejection. Server-side tracking details and event-ID mismatches are also checked where the captured requests provide the relevant evidence.

Supported tracking includes GA4, Google Ads, Meta, TikTok, X, LinkedIn, Microsoft Advertising, Criteo, Pinterest, Snapchat, Klaviyo, Adobe Analytics, Matomo, and Piwik PRO events. Microsoft Clarity and Hotjar loads are identified with their project or site IDs.

How it works

The model receives a goal and a text representation of the page, then acts through browser operations such as navigation, clicking, filling, selection, scrolling, and waiting. Playwright performs those operations one at a time. The browser_action and finish tools support this interaction.

During browsing, requests to supported collection endpoints are parsed into normalized hits and associated with the journey step that caused them. DataLayer activity, including consent commands, is captured through an initialization script. Collection requests are answered locally by default so test hits do not reach the corresponding real platform accounts. Host-recognized loads such as Clarity and Hotjar can still leave the browser.

Deterministic rules perform the measurement checks without model calls, which makes the results reproducible. The model then explains the findings and suggested corrections. Consent scenarios can open the starting page with accept-all, reject-all, and analytics-only choices in fresh browsers when the consent platform is supported.

Setup and configuration

The AI Tag Debugger MCP server can be used from a terminal or CI pipeline with an API key for Anthropic, OpenAI, Google Gemini, an OpenAI-compatible provider, or a local Ollama deployment. It can also be used through an MCP-capable chat application, where that application's model performs the audit instead of a separately configured API provider.

Platform selection is optional. By default, GA4, Google Ads, Meta, TikTok, and platforms detected on the site are checked. A fixed provider list can be supplied through the audit configuration or MCP start_audit and run_audit tools. Consent scenarios can be disabled with "consent_scenarios": false.

A gtm_container export adds GTM tag and trigger diagnostics, including paused tags, failed conditions, exception triggers, and denied consent. Click, form, visibility, and timer triggers are only evaluated when their corresponding GTM event reaches the captured dataLayer.

Tools and capabilities

  • Start or run audits through the MCP start_audit and run_audit tools.
  • Drive journeys with browser navigation, clicks, form filling, selection, scrolling, and waits.
  • Capture tracking hits, dataLayer pushes, consent commands, and journey steps.
  • Compare observed behavior with measurement plans and selected platforms.
  • Produce reports with findings, platform coverage, consent results, and skipped out-of-scope request counts.
  • Explain results in English or Turkish.

Limitations and notes

The tool cannot observe events that a GA4 server container forwards from another host when those events never pass through the browser; the report marks this limitation. Analytics-only consent testing is supported for OneTrust and Cookiebot, but not for every consent platform. Consent scenarios are skipped when no answerable banner is present or when a saved site is replayed.

Platform-specific checks depend on captured browser requests. Requests to platforms excluded from a fixed selection are answered locally, omitted from the timeline and checks, and reported only as counts. The project is MIT licensed.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about AI Tag Debugger

AI Tag Debugger is an MCP server that connects an AI model to a real browser and website tracking systems for QA audits. Its main tools include `start_audit`, `run_audit`, `browser_action`, and `finish`; they drive journeys, capture analytics and advertising hits, inspect dataLayer activity, and report measurement or consent problems.

It states that the tool can run from a terminal or CI pipeline with a supported model API key, or through an MCP-capable chat application using that application's model.

It parses events from GA4, Google Ads, Meta, TikTok, X, LinkedIn, Microsoft Advertising, Pinterest, Snapchat, Criteo, Klaviyo, Adobe Analytics, Matomo, and Piwik PRO. It also identifies Microsoft Clarity and Hotjar tag loads.

Yes, it tests accept-all, reject-all, and analytics-only scenarios when the consent setup supports them. Analytics-only testing is supported for OneTrust and Cookiebot; other supported consent platforms can still be tested for the available choices.

Yes, a `gtm_container` export adds tag and trigger diagnostics. Reports can identify paused tags, missing dataLayer trigger events, failed conditions, exception triggers, denied consent, and cases where the tag fired but its resulting hit remains incorrect.

Related MCP servers

All in Marketing All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAI Tag Debugger AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/analitikisler-ai-tag-debugger?style=directory)](https://allmcps.com/mcp/analitikisler-ai-tag-debugger)
HTML Embed
<a href="https://allmcps.com/mcp/analitikisler-ai-tag-debugger"><img src="https://allmcps.com/api/badge/analitikisler-ai-tag-debugger?style=directory" alt="AI Tag Debugger on AllMCPs" /></a>