Hosting

Community-maintained

Transport

Not documented

Endpoint

Local process; no hosted endpoint documented

Authentication

Google Search Console uses the service-account or OAuth setup described by the maintainer; optional GA4, CrUX, Bing, IndexNow, and SERP tools have separate provider credentials. Keep keys in a local secret store.

Requirements

• Python 3.11 or newer and uv/uvx.
• Google Search Console access and a supported service-account or OAuth credential setup from the maintainer guide.
• Google Analytics, CrUX, Bing, IndexNow, or SERP provider credentials are needed only for the corresponding optional tool families.

Setup steps

1. Run the published package with uvx gsc-mcp-tools (or install it as described in the maintainer installation guide).
2. Follow the linked Google setup guide to grant access to the Search Console properties and configure OAuth/service-account credentials.
3. Add the uvx command as a stdio MCP server in the client.
4. Set optional provider keys only for tool families you need, then inspect tools and configured account/property access.

95 tool rows were extracted from the current README table, while the README badge/headline claims 98. The remaining three names were not reconciled, so treat this displayed list as partial.

• get_capabilities

  List all available tools

  01
• serpapi_search

  Preview or explicitly capture one Google SERP on a verified free plan; durable attempt limits, no retries or paid fallback

  02
• serpapi_import_preview

  Qualify caller-supplied Google SERP JSON offline; retain missing fields and producer feature types

  03
• list_properties

  List all GSC properties

  04
• get_site_details

  Get details for a specific property

  05
• get_search_analytics

  Query search performance data

  06
• get_performance_overview

  Aggregate totals + top queries

  07
• search_change_breakdown

  Compare explicit equal Google windows with independent bounded page/query/country/device views, coverage and residuals

  08
• search_weekday_reference

  Default since 1.4.0: disjoint Google windows aligned by weekday and ending by Pacific J-3. Version 1.5.0 adds optional annual/robust references and mixed/undetermined results; descriptive, no causal attribution

  09
• compare_search_periods

  Compare two consecutive periods

  10
• get_search_by_page_query

  Performance broken down by page and query

  11
• get_advanced_search_analytics

  Flexible query with custom dimensions and filters

  12
• analytics_anomalies

  Z-score anomaly detection on daily clicks

  13
• discover_performance

  Top pages by impressions in Google Discover

  14
• news_performance

  Top pages by impressions in Google News

  15
• search_type_breakdown

  Clicks and impressions split across web, Discover, News, image, video

  16
• ai_overviews_impact

  Generic Web search appearances; AI exposure unverified, explicit 400/403 limits

  17
• quick_wins

  Pages in positions 4-15 with CTR below benchmark

  18
• traffic_drops

  Declining clicks with metric-based candidate diagnoses, not causal proof

  19
• check_alerts

  Traffic concentration risks and ranking opportunities

  20
• seo_striking_distance

  Queries in positions 8-15, one push away from page 1

  21
• seo_cannibalization

  Queries split across pages (HHI score); search operators excluded by default since 1.3.1

  22
• seo_lost_queries

  Queries with a click drop >= 80% vs the previous period

  23
• inspect_url

  URL indexing status via URL Inspection API

  24
• batch_url_inspection

  Inspect up to 10 URLs at once

  25
• check_indexing_issues

  Inspect URLs and categorize by issue type

  26
• submit_url

  Request indexing for a single URL

  27
• submit_batch

  Request indexing for multiple URLs (true HTTP batch)

  28
• list_sitemaps

  List submitted sitemaps

  29
• submit_sitemap

  Submit a sitemap URL

  30
• sitemaps_get

  Fetch details for a single sitemap

  31
• sitemaps_delete

  Delete a submitted sitemap (with safety check)

  32
• sitemap_audit

  Fetch a sitemap and compare its URLs with 90 days of Search Analytics page rows; does not measure indexation

  33
• ga4_organic_landing_pages

  Sessions and engagement for organic landing pages

  34
• ga4_traffic_sources

  Sessions and conversions by channel, source and medium

  35
• ga4_ai_referrals

  Recorded assistant-attributed visits, exact source rules and coverage-gated shares

  36
• ga4_page_performance

  7 metrics per page path, optional CONTAINS filter

  37
• ga4_realtime

  Active users right now by screen, country and device

  38
• ga4_user_behavior

  Device, country and user-type breakdowns in one batch call

  39
• ga4_conversion_funnel

  Converting pages and event counts, optional event filter

  40
• ga4_funnel

  Multi-step funnel report via GA4 v1alpha RunFunnelReport, conversion rate per step

  41
• traffic_health_check

  Equal requested dates, zero/empty/unavailable states and coverage-gated heuristic ratios

  42
• page_analysis

  GSC+GA4 join per page with opportunity score, sorted by priority

  43
• page_health_score

  Composite 0-100 score (GSC 30 pts, GA4 25 pts, CrUX 25 pts, schema 20 pts), graceful degradation per component

  44
• content_brief

  Per-page top queries, question queries, and GA4 session data for content planning

  45
• crux_page_vitals

  Real-user Core Web Vitals (LCP, INP, CLS, FCP, TTFB) for a URL from the Chrome UX Report API

  46
• crux_history

  Historical Core Web Vitals trend (weekly data points) for a URL

  47
• schema_validate

  Fetch any public URL and validate its JSON-LD schemas; suggests missing schemas by URL pattern

  48
• crawl_log_audit

  Since 1.5.0: bounded local common/combined logs, masked paths/IPs, declared bots and optional current Google IP membership; no indexing inference

  49
• crawl_snapshot_import

  Optional site-owned SiteOne storage, bounded details, exact-URL reconciliation and explicit cleanup

  50
• crawl_diff

  Exact observed inventory membership and compatible imported field differences; no deletion/indexing inference

  51
• indexing_evidence_matrix

  Keep supplied per-URL inspection, HTML, GSC, inventory and log observations separate with unknown current indexing

  52
• crawl_import_preview

  Since 1.4.0: preview bounded caller-supplied SiteOne JSON in memory; no crawl, file/network access, secrets or GSC join

  53
• schema_generate

  Generate a Schema.org JSON-LD block for Reservation, OrderAction, DiscussionForumPosting, or ProfilePage

  54
• drift_baseline

  Capture a baseline snapshot of a page (title, H1-H3, schema, canonical, CWV) stored locally in SQLite

  55
• drift_compare

  Diff a live fetch against the stored baseline and apply 17 rules (8 CRITICAL, 6 WARNING, 3 INFO)

  56
• drift_history

  List previous comparison runs for a URL with triggered findings per run

  57
• editorial_audit

  FR/EN house-style warnings, localized excerpts and faithful rewrite guidance; caller plain/Markdown drafts since 1.4.0 with native source spans and bounded parsing; no AI-authorship score

  58
• rewrite_fidelity_check

  Since 1.4.0: protected literals and qualifier review candidates; semantic fidelity and factual truth remain unassessed

  59
• seo_change_impact

  Since 1.4.0: declared event and descriptive Google before/after evidence; no persistence or causal effect

  60
• content_quality

  Fetch a URL for local filler, density, repetition and thin-content heuristics; requires independent evaluation

  61
• hreflang_audit

  Fetch a URL and validate its hreflang implementation: x-default, ISO 639-1 codes, region codes, self-ref, protocol consistency

  62
• page_technical_audit

  Fetch a URL and audit meta tags (title, description, canonical, robots), viewport, HTML lang, security headers, robots.txt Googlebot access

  63
• preload_audit

  Audit Speculation Rules, bfcache eligibility, and LCP preload signals: inline speculationrules blocks, Speculation-Rules header, link preload tags, deprecated prerender, cache-control blockers

  64
• crux_lcp_subparts

  Decompose LCP into four subparts (TTFB, resource load delay, duration, render delay) with dominant phase identification for targeted CWV remediation

  65
• indexnow_submit

  Submit URLs to IndexNow (Bing, Yandex, Seznam, Naver) via one POST; SSRF-safe URL validation, skipped-invalid count, ok/partial/error verdict

  66
• parasite_risk

  Scan URL paths for parasite SEO patterns matching Google's 2024-11-19 site-reputation policy: sponsored/affiliate sections, Forbes Advisor, CNN Underscored patterns, affiliate query params

  67
• ai_visibility_audit

  Check robots.txt and llms.txt; version 1.3.1 checks 10 agents, including ClaudeBot, Claude-User and Claude-SearchBot

  68
• gbp_deprecation_lint

  Scan a page for deprecated Google Business Profile features: .business.site links, Reserve with Google, GBP appointment widgets

  69
• pagespeed_audit

  Run a PageSpeed Insights API v5 audit: Lighthouse performance score, Core Web Vitals, top 3 improvement opportunities (requires GOOGLE_API_KEY)

  70
• heading_audit

  Audit heading structure: H1 uniqueness, level jumps (H2 to H4), title vs H1 word-for-word duplication, headings carrying no information, words per H2

  71
• link_targets_audit

  Observe bounded internal destination HTTP statuses and redirect hops while preserving source anchors; no recursive crawl

  72
• internal_links_audit

  Audit a page's internal links weighted by zone (body, nav, footer, header, aside): targets linked only from footer/nav, generic and empty anchors, internal nofollow, self-links

  73
• link_equity_map

  Crawl the top pages by impressions, build the internal link graph, cross it with GSC: pages at position 11-20 with no body inbound link, orphan candidates, footer-only targets, hubs

  74
• prune_candidates

  Classify pages by measured traffic (has_traffic, impressions_no_clicks, low_impressions, zero_impressions) before any pruning call; a page with clicks is never a candidate

  75
• bing_sites_list

  List sites visible to the Bing account and their observed verified state

  76
• bing_query_stats

  Query performance in Bing's observed rolling window

  77
• bing_page_stats

  Page performance in Bing's observed rolling window

  78
• bing_page_query_stats

  Query performance for one page

  79
• bing_rank_traffic_stats

  Daily clicks and impressions; no rank field is inferred

  80
• bing_crawl_stats

  Dated crawl counters in the requested local window

  81
• bing_crawl_issues

  Crawl issue flags; non-empty live item shape remains unverified

  82
• bing_crawl_settings_get

  Observed crawl-rate setting from the partial contract

  83
• bing_url_info

  Observed URL fields and last crawl date, without an indexation verdict

  84
• bing_url_traffic

  URL clicks, impressions and derived CTR

  85
• bing_feeds_list

  List registered Bing feeds

  86
• bing_feed_details

  Return every observed feed-detail row

  87
• bing_url_submission_quota

  Return quota integers with total-versus-remaining semantics marked unknown

  88
• bing_link_counts

  Backlink count page; nested runtime shape remains unverified

  89
• bing_url_links

  Backlinks for one URL; nested runtime shape remains unverified

  90
• bing_url_submit

  Submit one same-origin URL; acceptance does not prove indexation

  91
• bing_urls_submit_batch

  Validate a batch, then refuse it while quota semantics remain unknown

  92
• bing_feed_submit

  Submit one same-origin feed without claiming crawl or indexation

  93
• bing_feed_remove

  Remove a registered same-origin feed after explicit confirm=true; runtime contract unverified

  94
• compare_search_engines

  Compare query or page metrics; deltas require equal exact observed windows and positions stay side by side

  95

This server’s available tools can vary by account, permissions, or configuration. The list shown is not its full runtime catalog.

• maintainer source

  Maintainer README explicitly lists 95 exact tools.

Documentation checked 2026-10-28T00:00:00Z. Connection has not been runtime tested.