Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Tag Pilot GTM 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.
93/100
trust score
24
tools declared
local
runs on your machine
—
downloads a day
What it does
Free, read-only Google Tag Manager: containers, tags, diffs vs live, audits. No GCP setup.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user tag-pilot-gtm-mcp '--' npx -y @tagpilot/gtm-mcp
# 2 — ask your agent for something these tools do
# get_account_summaries, get_property_details, list_google_ads_links and 21 more
Tag Pilot GTM costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TAAll 3 servers
tagpilot3 servers
2 categories
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 Tag Pilot GTM 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 tag-pilot-gtm-mcp '--' npx -y @tagpilot/gtm-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 asks of you
Nothing is required, but it can take TAGPILOT_API_KEY (Optional. Leave unset: the first question connects this device to your free Tag Pilot account in the browser. Set a gtm:mcp key (tpk_…) only for CI or headless setups.), GTM_MCP_NO_BROWSER (Set to 1 to only return the Google sign-in link (open it in any browser) instead of opening a browser.), GTM_MCP_AUTH_WAIT_SECONDS (How long a tool call waits for the browser sign-in before returning the link.) if you want to set them.
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
24 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Lists every Google Analytics account and GA4 property the signed-in Google account can read, with property IDs. Start here to find the property_id for other tools.
No parameter schema on file.
Returns a GA4 property's settings (time zone, currency, industry, service level: standard or 360) and its data streams, including web measurement IDs (G-XXXX) and default URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — |
Lists the Google Ads accounts linked to a GA4 property (customer IDs, personalization setting, who created the link).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — |
Lists the reporting annotations of a GA4 property (notes on dates such as releases, tracking changes or campaigns, plus system-generated ones). Useful to explain jumps in data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — |
Lists the custom dimensions and metrics of a GA4 property with the API names to use in run_report (e.g. "customEvent:payment_type", "customUser:plan").
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — | |
| include_standard | boolean | no | Also return built-in dimensions and metrics. Default false. |
| search | string | no | Case-insensitive filter on API name, UI name and category, e.g. "item" or "revenue". |
Tag Pilot tracking-health check. Counts purchase events per transaction_id to find duplicated purchases (usually thank-you page reloads,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — | |
| date_range | yes | — | |
| top | integer | no | How many duplicated transaction IDs to list. Default 20. |
Tag Pilot tracking-health check. Shows how sessions split by default channel group and flags attribution problems: the share of "Unassigned"
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — | |
| date_range | yes | — |
Runs a Google Analytics 4 report (Data API runReport): metrics broken down by dimensions over date ranges, with optional filters, sorting and paging.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — | |
| date_ranges | yes | — | |
| dimensions | array | no | — |
| metrics | array | yes | Metric API names, e.g. "activeUsers", "sessions", "eventCount", "keyEvents", "ecommercePurchases", "purchaseRevenue", "engagementRate", "screenPageViews". |
| dimension_filter | no | Filter on dimensions (applied before aggregation), e.g. [{"field": "eventName", "op": "exact", "value": "purchase"}]. | |
| metric_filter | no | Filter on metrics (applied after aggregation), e.g. [{"field": "sessions", "op": "gt", "value": 100}]. | |
| order_bys | array | no | Sort order, e.g. [{"field": "sessions", "desc": true}] or [{"field": "date"}]. |
| limit | yes | — | |
| offset | integer | no | Row offset for paging (use next_offset from a previous result). |
| metric_aggregations | array | no | Also return totals / maximums / minimums across all rows. |
| keep_empty_rows | boolean | no | Include rows whose metrics are all 0. Default false. |
| currency_code | string | no | ISO 4217 code, e.g. "EUR". Default: the property currency. |
| return_property_quota | yes | — |
Realtime data for the last 30 minutes (60 on GA4 360): active users and events right now. Good for checking that a tracking change is live.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — | |
| dimensions | array | no | — |
| metrics | array | yes | Realtime metrics: "activeUsers", "eventCount", "keyEvents", "screenPageViews". |
| dimension_filter | no | — | |
| metric_filter | no | — | |
| order_bys | array | no | — |
| limit | yes | — | |
| minute_ranges | array | no | Default: the last 30 minutes. Two ranges are allowed (e.g. last 5 vs last 30 minutes). |
| return_property_quota | yes | — |
Funnel exploration (Data API v1alpha runFunnelReport): how many users reach each step and where they drop off.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| property_id | yes | — | |
| date_ranges | yes | — | |
| steps | array | yes | Funnel steps in order (2–10). Each needs event_name and/or conditions. |
| open_funnel | boolean | no | Open funnel: users can enter at any step. Default false (closed: everyone starts at step 1). |
| breakdown_dimension | string | no | Split each step by a dimension, e.g. "deviceCategory" or "sessionDefaultChannelGroup". |
| breakdown_limit | integer | no | Max breakdown values. Default 5. |
| next_action_dimension | string | no | Show what users did next after each step: "eventName", "pagePath", "pageTitle", "unifiedScreenName" (and a few more). |
| trended | boolean | no | Also return a day-by-day (trended) funnel. Default false. |
| dimension_filter | no | Limit the funnel to users matching these dimension conditions (e.g. a country). | |
| limit | yes | — | |
| return_property_quota | yes | — |
Tag Manager accounts you can read, with their IDs.
No parameter schema on file.
Containers in an account: ID, GTM-XXXX public ID, name, web or server.
No parameter schema on file.
Workspaces of a container (where unpublished changes live).
No parameter schema on file.
Tags with their triggers, triggers, variables, templates and folders of the live version, a workspace or a version.
No parameter schema on file.
One tag in full: parameters, triggers, consent settings, sequencing and the variables it uses.
No parameter schema on file.
One trigger in full: conditions, and the tags that use it.
No parameter schema on file.
One variable (or built-in variable) in full, and what uses it.
No parameter schema on file.
What uses a variable, trigger, tag, template or folder.
No parameter schema on file.
Container versions with entity counts, and which one is live.
No parameter schema on file.
The published version: name, description and contents.
No parameter schema on file.
What publishing a workspace would add, change or delete compared with the live version.
No parameter schema on file.
Tag Pilot check: tags that never fire, unused triggers/variables, consent settings, duplicate Google tags, unpublished changes.
No parameter schema on file.
Connect this computer: returns a link and code to approve in your browser (free Tag Pilot account + read-only Tag Manager access).
No parameter schema on file.
Whether this computer is connected, waiting for approval, or needs connecting.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 Tag Pilot GTM 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 93 / 100
Release 0.1.0 · scanned 14 Nov 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 score93
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest57608da9faf0a0e5c818959be8e3ef7974b06d21e3b3fb8763d43f148c130557
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 (14 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>".
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| connect | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| connection_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| diff | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| audit_container | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_accounts | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_containers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_workspaces | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_container | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_versions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_live_version | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_tag | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_trigger | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_variable | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| find_references | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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 digest57608da9faf0a0e5
Scanned2026-11-14
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 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
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 Tag Pilot GTM 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.