# @analitikisler/ai-tag-debugger

Open-source AI agent that QA-tests your website's analytics, ad and consent tracking (GA4, GTM, Google Ads, Meta, TikTok). Bring your own model (Claude, OpenAI, Gemini) or use it from your chat app over MCP.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.18.0
- **Author:** Analitik İşler
- **License:** MIT
- **npm:** @analitikisler/ai-tag-debugger
- **Source:** https://github.com/analitikisler/ai-tag-debugger
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 2 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-22T07:30:17.140Z
- **Version scanned:** 0.18.0
- **CVEs:** none found by OSV at scan time

## Tools

8 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `browser_action` — Perform one action in the browser. Returns the updated page. Actions: goto (url, absolute or relative to the current page), click (ref or text), fill (ref or te
- `finish` — End the journey. Call when the goal is reached, or when it cannot be reached.
- `start_audit` — Opens a fresh browser on a website and starts recording every analytics and ad tracking request (GA4, Google Ads, Meta, TikTok) and dataLayer push. Tracking req
- `get_page` — Returns the current page view of an open audit without doing anything.
- `finish_audit` — Closes the browser, checks every captured hit against the plan (missing events, missing parameters, duplicates, hits before consent, Consent Mode defaults, emai
- `make_plan` — Explores a website and drafts its measurement plan: the events, parameters and user properties it should track. Same as `aitd plan --site`. The plan is saved (u
- `what_changed` — Returns only the "since last run" diff for a site: which problems were fixed and which are new in its newest saved run (`aitd run`) compared with the run before
- `run_audit` — Runs every journey in a ai-tag-debugger config file and writes the report. With against, the run is checked against a saved plan and, if the config has no journ

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"ai-tag-debugger\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@analitikisler/ai-tag-debugger\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 13, ceiling 31 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40analitikisler%2Fai-tag-debugger
- Install plan: https://forgeregistry.com/api/v1/packages/%40analitikisler%2Fai-tag-debugger/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40analitikisler%2Fai-tag-debugger
- HTML page: https://forgeregistry.com/registry/%40analitikisler%2Fai-tag-debugger
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.