Model Context Protocol server for Rollbar
Nothing to run from here
AI Tag Debugger is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
7
tools declared
local
runs on your machine
—
downloads a day
What it does
QA-tests your site analytics, ad and consent tags (GA4, GTM, Ads, Meta, TikTok) from chat.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ai-tag-debugger-mcp '--' npx -y @analitikisler/ai-tag-debugger mcp
# 2 — ask your agent for something these tools do
# start_audit, browser_action, get_page and 4 more
AI Tag Debugger costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ANAll 1 server
analitikisler1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts AI Tag Debugger as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user ai-tag-debugger-mcp '--' npx -y @analitikisler/ai-tag-debugger mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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 requests are answered locally, so no test data reaches the real analytics or ad accounts. Returns an audit_id and the first page view. Then…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site | string | yes | The page to open, e.g. https://staging.example.com/ |
| journey | string | no | A ready-made journey (…), which comes with its goal and the events to expect, or a short name for your own journey, e.g. newsletter. |
| viewport | string | no | Default desktop. |
| allowed_hosts | array | no | Other hosts the journey may visit, e.g. a hosted checkout like checkout.example-payments.com. The browser stays on the site's own host and subdomains otherwise. |
| providers | array | no | Tracking providers to check. Default … plus any other known platform the site sends to. When given, requests to the others are still answered locally, but they are only counted, not shown or checked. |
Performs one action in the audit's browser and returns the updated page plus the tracking hits that action sent. Actions: goto (url), click (ref or text), fill (ref or text, value), select (ref or text, value), scroll (value = down or up), wait (value = milliseconds). Refs come from the latest…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
| action | string | yes | — |
| ref | integer | no | Element ref for click, fill and select. |
| text | string | no | Instead of ref: the element's visible text or label, e.g. "Book now". |
| value | string | no | Text to type, option to select, or milliseconds to wait. |
| url | string | no | Destination for goto, absolute or relative to the current page. |
| reason | string | yes | Short description of the step, e.g. 'Add the first product to the cart'. Shown in the report. |
| accepts_consent | boolean | no | True only when this click accepts the cookie or consent banner. |
| rejects_consent | boolean | no | True only when this click rejects or declines all cookies on the consent banner. |
Returns the current page view of an open audit without doing anything.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
Closes the browser, checks every captured hit against the plan (missing events, missing parameters, duplicates, hits before consent, Consent Mode defaults, emails sent in plain text, unplanned events) and writes the report with the event timeline. Returns the findings. The plan is what should be…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | string | yes | — |
| completed | boolean | yes | Whether the journey reached its goal. |
| note | string | yes | One sentence on how the journey ended. |
| measurement_plan | string | no | — |
| against | string | no | A saved plan to check against: latest (or last), first, a plan ID such as 2026-10-16_0627, or on a local server a path to a plan file or folder. Plans are the ones saved by aitd plan --site <url>. T |
| events | array | no | Only check these events, e.g. ["purchase", "add_to_cart"]. On your own journey, these events are also expected to fire. |
| language | string | no | Report language. Default en. |
| branding | boolean | no | Set false to leave the Analitik İşler logo and credit line out of the report. |
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 (use its ID as against in finish_audit to check an audit against it) and the events are returned. Uses the AI provider configured on the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site | string | yes | The site to plan, e.g. https://www.example.com/ |
| topic | string | no | Limit the plan to one kind of event: …. Default: the whole plan. |
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 it. Compares plan coverage when both runs were checked against a plan, health findings otherwise. Does not browse or use an AI. Use it to…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site | string | yes | The site, e.g. https://www.example.com/. Its saved runs are the ones in the data folder of the computer running this server. |
| language | string | no | Language of the answer. Default en. |
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 journeys, walks the journeys derived from that plan. With scripted true, it replays each journey's fixed steps and needs no API key. Otherwise…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| config | string | yes | Path to the config file, e.g. ai-tag-debugger.config.json |
| against | string | no | A saved plan to check against: latest (or last), first, a plan ID such as 2026-10-16_0627, or on a local server a path to a plan file or folder. Plans are the ones saved by aitd plan --site <url>. T |
| scripted | boolean | no | Replay fixed steps instead of browsing with an AI model. Default true. |
| language | string | no | — |
| branding | boolean | no | Set false to leave the Analitik İşler logo and credit line out of the report. |
| providers | array | no | Tracking providers to check. Default … plus any other known platform the site sends to. When given, requests to the others are still answered locally, but they are only counted, not shown or checked. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AI Tag Debugger or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.16.0 · scanned 18 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestb116e521c26a5eb0b008967e7382a7fa79b005a0102545673704b76d3620b590
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (7 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 7 recovered tools are registered only when opts.allowFiles holds (src/mcp.js:377) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 6.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
6 tools are registered unconditionally · 1 more only when opts.allowFiles holds (src/mcp.js:377) — typically when a key or option is configured. All 7 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| start_audit | no tags | |
| browser_action | no tags | |
| get_page | untrusted-input | untrusted-input: keyword "get_page" |
| finish_audit | no tags | |
| make_plan | no tags | |
| what_changed | no tags | |
| run_audit conditional | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestb116e521c26a5eb0
Scanned2026-10-18
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.16.0. Pin a release below and the command asks for exactly that one.
0.16.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish AI Tag Debugger can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.