Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Seo Audit Console 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.
96/100
trust score
223
downloads a day
local
runs on your machine
3k
downloads in 30d
What it does
The complete technical SEO audit at conversation speed: Google Search Console history + a first-party crawl + on-demand DataForSEO, merged into one prioritised audit inside Claude - 90 checks ranked by recoverable clicks, with paste-ready fixes, keyword a
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GOOGLE_APPLICATION_CREDENTIALS=${GOOGLE_APPLICATION_CREDENTIALS}' --transport stdio seo-audit-console-mcp '--' npx -y @houtini/seo-audit-console
# 2 — ask your agent for something these tools do
# seo_audit_help, composition_cookbook, list_checks and 55 more
It needs GOOGLE_APPLICATION_CREDENTIALS: this reads it from your environment, so export it first.
Seo Audit Console costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Seo Audit Console as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GOOGLE_APPLICATION_CREDENTIALS (Path to the Google service-account JSON key with Search Console access) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx GOOGLE_APPLICATION_CREDENTIALS … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GOOGLE_APPLICATION_CREDENTIALS=${GOOGLE_APPLICATION_CREDENTIALS}' --transport stdio seo-audit-console-mcp '--' npx -y @houtini/seo-audit-consoleReconnect, 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
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GOOGLE_APPLICATION_CREDENTIALS — Path to the Google service-account JSON key with Search Console access.. You set it in your own client’s config, on your machine — this marketplace never holds it.
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
58 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.
Overview of every tool/feature with an example prompt for each. Start here.
No parameter schema on file.
The full data-surface map (every source: grain, dimensions, join keys, freshness, cost) plus worked multi-source recipes and novel combinations, in this server\
No parameter schema on file.
List the technical-SEO check categories this server can evaluate.
No parameter schema on file.
No parameter schema on file.
No args: report the folder where per-property crawl/audit databases are saved. With
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Run a single named check (see list_checks) and return its affected URLs + evidence. Token discipline:
No parameter schema on file.
Direct read-only access to the property database — the composition layer\
No parameter schema on file.
Run a local cross-encoder reranker (ms-marco-MiniLM-L-6-v2, downloaded once to a cache, no Python) over each ranking page\
No parameter schema on file.
Assemble a GROUNDED writing brief for a page so YOU (the assistant) can draft the fix — no bundled LLM. Returns the ranking-query gap, the page\
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Return the canonical url_key used to join GSC data to crawl data.
No parameter schema on file.
List Google Search Console properties accessible to the service account.
No parameter schema on file.
No parameter schema on file.
Poll a sync job by id, or omit to list recent jobs.
No parameter schema on file.
Update just the GSC URL Inspection data (coverage, indexing, Google-vs-declared canonical, last crawl) for top URLs into url_inspection. Quota-limited — samples top pages by clicks. Async job. For a full refresh use refresh_property. Grain: one row per inspected URL. Joins: url_key → pages/GSC.
No parameter schema on file.
No parameter schema on file.
Poll a crawl job by id, or omit to list recent jobs.
No parameter schema on file.
[Paid: Keywords API, cheap, cached 20d | Use for: demand sizing] True monthly search volume + CPC + competition for keywords (DataForSEO KEYWORDS_DATA). Served from a 20-day cache; live calls are serialised. Default location: United States (2840).
No parameter schema on file.
[Paid: SERP call PER KEYWORD - only for clicked/explicit keywords, never lists | Use for: the SERP context of a single keyword] People Also Ask questions and related searches for a keyword (DataForSEO SERP). Powers click-through
No parameter schema on file.
No parameter schema on file.
[Google News is FREE (no key); DataForSEO adds a paid, richer Google News SERP | Use for: what has been PUBLISHED on a topic — freshness,
No parameter schema on file.
[Paid: Keywords API, cheap, cached 20d | Use for: seasonality +
No parameter schema on file.
No parameter schema on file.
The content marketer\
No parameter schema on file.
[Paid: DataForSEO SERP per page (~$0.004 each, plus a small refundable surcharge for loading async AI Overviews), bounded to the batch | Use for: the deep
No parameter schema on file.
No parameter schema on file.
The content-recon to-do board. With no id: list to-dos (optionally filter by page or status), grouped by page with each page\
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
[Paid: Labs, cheap, cached 20d | Use for: page-level content gap vs named rival URLs] Find keywords that competitor pages rank for but your page does NOT (the content gap). Pass competitor URLs as
No parameter schema on file.
No parameter schema on file.
[Paid: Labs, cheap, cached 20d | Use for: where rival traffic actually lands] The top organic pages of ANY domain or subdomain, ranked by estimated traffic value (ETV): page, ranking-keyword count, ETV and top-3 / top-10 keyword counts. The Semrush-style
No parameter schema on file.
[Paid: Labs, cheap, cached 20d - ONE call replaces any keyword loop | Use for: full keyword footprint of a domain/page/folder] Every keyword a target ranks for in Google organic — scope it to a whole domain, a subdomain, ONE page (scope:url with the full URL), or a subfolder (scope:folder + folder:
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Write a self-contained, interactive dashboard HTML for a property (all data + charts inlined) to the reports folder, and return the file path. Open it in any browser or send it to a client — no server, no MCP-App host support needed. Run refresh_property (+ run_audit for findings) first.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
[Paid: Backlinks subscription (separate - 40204 = not activated), one cached call ~$0.024 | Use for: prospect list for link outreach] Answers
No parameter schema on file.
The full audit check catalogue (the list_checks data) rendered as markdown: every check with category, severity, labels, certainty, fix type and its one-line fix.
No parameter schema on file.
Ingest the DataForSEO over-time sequence (monthly rank distribution + ETV) into rank_history, so rank charts have a real time axis reconciled with GSC. DataForSEO Labs call — cached 20 days. Pass location once (e.g.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
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 Seo Audit Console 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 96 / 100
Release 1.0.1 · scanned 3 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 score96
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest70c8e3d75f72f8171055785dbc32b84ca1add3dbe80d85d2af091ef08cfd4770
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (58 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| seo_audit_help | no tags | |
| composition_cookbook | no tags | |
| list_checks | no tags | |
| list_templates | untrusted-input | untrusted-input: keyword "crawl" |
| data_location | untrusted-input | untrusted-input: keyword "crawl" |
| data_storage | untrusted-input | untrusted-input: keyword "crawl" |
| run_audit | untrusted-input | untrusted-input: keyword "crawl" |
| query_audit | no tags | |
| query_data | untrusted-input | untrusted-input: keyword "crawl" |
| score_passages | untrusted-input | untrusted-input: keyword "crawl", parameter "url" with "downloads" in the description |
| render_pages | untrusted-input | untrusted-input: keyword "crawl", parameter "url" with "crawl" in the description |
| find_duplicates | untrusted-input | untrusted-input: keyword "crawl" |
| draft_content | no tags | |
| detect_changes | no tags | |
| check_agent_readiness | untrusted-input | untrusted-input: keyword "crawl" |
| fix_finding | no tags | |
| normalize_url | untrusted-input | untrusted-input: keyword "crawl", parameter "url" with "crawl" in the description |
| list_properties | no tags | |
| sync_gsc | untrusted-input | untrusted-input: keyword "fetch" |
| check_sync_status | untrusted-input | untrusted-input: keyword "fetch" |
| inspect_urls | no tags | |
| start_crawl | untrusted-input | untrusted-input: keyword "fetch" |
| probe_urls | untrusted-inputstate-write | untrusted-input: keyword "fetch", parameter "url" with "fetch" in the description; state-write: handler runs a INSERT statement at dist/server.js:1005 |
| triage_404s | untrusted-input | untrusted-input: keyword "crawl" |
| check_crawl_status | untrusted-input | untrusted-input: keyword "crawl" |
| keyword_volume | no tags | |
| related_terms | no tags | |
| youtube_discovery | no tags | |
| news_discovery | untrusted-input | untrusted-input: keyword "rss" |
| topic_trend | no tags | |
| trend_categories | no tags | |
| suggest_pages | untrusted-input | untrusted-input: keyword "crawl" |
| content_opportunities | no tags | |
| recon_targets | untrusted-input | untrusted-input: keyword "crawl", parameter "url" with "fetches" in the description |
| save_recon_todo | no tags | |
| recon_todos | state-write | state-write: handler runs a UPDATE statement at dist/server.js:1396 |
| keyword_list | no tags | |
| search_intent | state-write | state-write: handler runs a INSERT statement at dist/server.js:1481 |
| page_lighthouse | state-write | state-write: handler runs a INSERT statement at dist/server.js:1535 |
| competitors_domain | no tags | |
| page_intersection | no tags | |
| domain_visibility | no tags | |
| top_pages | untrusted-input | untrusted-input: keyword "crawl" |
| ranked_keywords | no tags | |
| serp_features | no tags | |
| market_sizing | no tags | |
| topic_gaps | no tags | |
| portfolio | untrusted-input | untrusted-input: keyword "fetch" |
| refresh_portfolio | untrusted-input | untrusted-input: keyword "fetch" |
| schedule_portfolio_refresh | no tags | |
| export_report | no tags | |
| serve_dashboard | no tags | |
| open_dashboard | no tags | |
| pull_backlinks | untrusted-input | untrusted-input: keyword "fetch" |
| link_intersect | no tags | |
| resolve_entities | no tags | |
| track_ranks | no tags | |
| sync_crux | 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 digest70c8e3d75f72f817
Scanned2026-11-03
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 1.0.1. Pin a release below and the command asks for exactly that one.
1.0.1
3 Nov 2026
latestNo release note was published with this version.
1.0.0
31 Oct 2026
No release note was published with this version.
0.17.0
25 Oct 2026
No release note was published with this version.
0.16.2
18 Oct 2026
No release note was published with this version.
0.16.1
17 Oct 2026
No release note was published with this version.
0.15.0
17 Oct 2026
No release note was published with this version.
0.13.0
14 Oct 2026
No release note was published with this version.
0.12.1
6 Oct 2026
No release note was published with this version.
0.11.1
6 Oct 2026
No release note was published with this version.
0.10.0
29 Sep 2026
No release note was published with this version.
0.9.1
23 Sep 2026
No release note was published with this version.
0.8.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Seo Audit Console 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.