Google Search Console integration for Model Context Protocol (MCP)
Google Webtools 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.
What it does
Google Search Console + GA4 for AI agents: properties, reports, indexing, verification, SEO.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GOOGLE_SERVICE_ACCOUNT_KEY=${GOOGLE_SERVICE_ACCOUNT_KEY}' --transport stdio google-webtools-mcp '--' docker run -i --rm -e GOOGLE_SERVICE_ACCOUNT_KEY ghcr.io/stufently/google-webtools-mcp
# 2 — ask your agent for something these tools do
# find_quick_wins, find_declining_content, find_ctr_opportunities and 36 more
It needs GOOGLE_SERVICE_ACCOUNT_KEY: this reads it from your environment, so export it first.
Google Webtools costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Google Webtools as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It has not been scanned here, so read the surface, and its source, before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Docker installed and running. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GOOGLE_SERVICE_ACCOUNT_KEY (Google service account key, the whole JSON as one string. The account must be added as a user in Search Console and GA4) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx GOOGLE_SERVICE_ACCOUNT_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GOOGLE_SERVICE_ACCOUNT_KEY=${GOOGLE_SERVICE_ACCOUNT_KEY}' --transport stdio google-webtools-mcp '--' docker run -i --rm -e GOOGLE_SERVICE_ACCOUNT_KEY ghcr.io/stufently/google-webtools-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GOOGLE_SERVICE_ACCOUNT_KEY — Google service account key, the whole JSON as one string. The account must be added as a user in Search Console and GA4.. You set it in your own client’s config, on your machine — this marketplace never holds it.
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.
39 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.
Find "money on the table" SEO opportunities as query/page pairs: those ranking well but underperforming on clicks, those almost on page 1, and positions where a small push yields big gains
No parameter schema on file.
Find pages and queries losing traffic: compares the current period against the previous one, reporting declining pages and declining queries as two separate rankings, to surface content that needs attention before it drops further
No parameter schema on file.
Find pages with click-through rates significantly below industry benchmarks for their position, with specific recommendations to improve each one
No parameter schema on file.
Discover content creation opportunities: queries ranking on wrong pages, high-impression zero-click queries, new emerging queries, and topics needing dedicated pages
No parameter schema on file.
Intent-based content planning: analyzes search queries by user intent (questions, comparisons, problems, buying signals) and recommends what content to create next, grouped by topic clusters
No parameter schema on file.
Generate a comprehensive weekly SEO performance report with trends, growers, decliners, quick wins, sitemap health, and prioritized recommendations
No parameter schema on file.
Run a comprehensive SEO health check with an overall A-F letter grade, sub-scores for traffic trends, CTR efficiency, position distribution, and sitemap health, plus prioritized recommendations
No parameter schema on file.
Inspect a single URL for indexing status, mobile usability, and rich results
No parameter schema on file.
Inspect multiple URLs for indexing status in batch (max 50)
No parameter schema on file.
Audit top pages by traffic for indexing issues, canonical mismatches, and mobile problems
No parameter schema on file.
Query raw Google Search Console search analytics data with flexible parameters
No parameter schema on file.
Get a high-level performance overview with period-over-period comparison
No parameter schema on file.
Compare search performance between two custom date periods side by side
No parameter schema on file.
Get top search queries by clicks with CTR benchmark analysis
No parameter schema on file.
Get top pages by clicks with CTR analysis
No parameter schema on file.
Get traffic breakdown by device type (desktop, mobile, tablet)
No parameter schema on file.
Categorize all queries by user intent, branded vs non-branded split, and position distribution
No parameter schema on file.
Find truly new and rapidly emerging queries by comparing the current period against the previous period
No parameter schema on file.
Detect keyword cannibalization: multiple pages competing for the same query
No parameter schema on file.
List all GA4 accounts and their properties accessible to the authenticated user
No parameter schema on file.
List all GA4 properties for a specific account
No parameter schema on file.
Get detailed information for a specific GA4 property
No parameter schema on file.
Create a new GA4 property under an account
No parameter schema on file.
Create a web data stream for a GA4 property and get the measurement ID
No parameter schema on file.
List all data streams for a GA4 property
No parameter schema on file.
Get detailed information for a specific data stream
No parameter schema on file.
Run a GA4 analytics report with specified metrics, dimensions, and date range
No parameter schema on file.
Run a GA4 realtime report showing current active users and activity
No parameter schema on file.
List all available GA4 dimensions and metrics for a property (including custom definitions)
No parameter schema on file.
List all sitemaps submitted for a Google Search Console property
No parameter schema on file.
Get detailed information about a specific sitemap including URL counts by content type
No parameter schema on file.
Submit a new sitemap to Google Search Console for a property
No parameter schema on file.
Remove a submitted sitemap from Google Search Console
No parameter schema on file.
List all Google Search Console properties with permission levels and types
No parameter schema on file.
Get detailed information for a specific Google Search Console property
No parameter schema on file.
Add a new site property to Google Search Console
No parameter schema on file.
Remove a site property from Google Search Console (permanent)
No parameter schema on file.
Get a verification token for a site using the specified verification method (FILE, DNS_TXT, META, or ANALYTICS)
No parameter schema on file.
Verify site ownership using a previously configured verification method
No parameter schema on file.
- 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 Google Webtools or to call it, at any volume.
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.
This listing ships as a container image. The scanner reads packages on npm and PyPI and public source; an image is neither, so there is no grade here — not a withheld one, an unmeasured one.
Release history
It installs from a container image rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 1.2.2.
No release note was published with this version.
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.
Any signed-in account that does not publish Google Webtools can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.