Organiq GEO
Server Details
Search Console and GA4 analysis (read-only Google): queries, decay, cannibalization, AI traffic.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- organiqgeo/organiq-plugin
- GitHub Stars
- 1
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 51 tools
Most tools have clearly distinct purposes, and the extensive descriptions help distinguish similar-sounding analytics operations. There is some potential overlap between score_opportunities and find_page_poaching_opportunities, between generate_seo_report and get_weekly_digest, and among the query-shape/long-tail tools, but these are separated by period, output, or analytical angle.
All names use snake_case with a verb_noun pattern, which is readable and predictable. The set mixes several verb families (get_, query_, list_, analyze_, find_, set_, request_, etc.), but they generally map coherently to purpose rather than being chaotic.
With 51 tools, the surface is far beyond typical MCP server scope and exceeds the 50+ threshold for an extreme mismatch. The domain is broad, but an agent must choose among too many narrowly differentiated analytics tools, increasing selection cost and failure risk.
The tool set covers the domain comprehensively: site summaries, timeseries, dimensions, queries/pages, audits, indexing, AI visibility, Bing/GA4 integrations, forecasting, reporting, and write operations for configuration. No obvious core Search Console/GEO workflow is missing.
Available Tools
51 toolsanalyze_cannibalizationQuery cannibalizationARead-onlyIdempotentInspect
Queries where 2+ pages of the property compete for the same search in the period. Per cluster: totals, Shannon entropy of impressions across pages (bits; higher = more even split = worse; level high >= 1.5, medium >= 1.0), normalized (0–1), winner (most clicks; tie: best position) and the contenders with clicks/impressions/ctr/position/impressionShare. Sorted by entropy and impressions. Protocol/host/hash variants of one URL are canonical hygiene, not cannibalization; brand + home + deep page is usually sitelinks. Use when asked which page should rank for a keyword. / Canibalização de queries.
Inputs: site (required), days, brand, limit, +9 more.
analyze_query_shapesQuery shapes (incl. AI-style)ARead-onlyIdempotentInspect
Classifies the period's queries into shapes and aggregates each: branded, question, comparison, transactional, local, longtail (5+ words), head (<= 2 words), other, with queries, clicks, impressions, ctr, position, shares, comparison (clicksChangePct, impressionSharePoints) and top example queries per shape. Also reports the "AI-style" split used by the Organiq dashboard (conversational marker or >= 5 words: the kind of query AI Overviews / AI Mode answer) — a proxy, since Search Console does not expose AI-feature data in the API. Shapes: branded = contains one of the property's branded terms; question = interrogative (how, what, why, como, o que, qual…); comparison = compares options (vs, best, melhor, diferença entre…); transactional = buying intent (price, buy, comprar, preço, promoção…); local = local intent (near me, perto de mim, address…); longtail = 5+ words without another marker; head = 2 words or fewer; other = 3–4 words without a marker. Use for intent mix, "how much of our demand is questions", GEO (generative engine) planning. / Formatos de query (perguntas, comparação, transacional, marca, longas "estilo IA") com shares e exemplos.
Inputs: site (required), days, brand, query, +8 more.
analyze_sampling_impactHidden (anonymized) clicksARead-onlyIdempotentInspect
How much of the property's traffic Search Console hides from the query/page rows because of anonymization: exact totals per day (no dimensions) minus the sum of the query × page rows = hidden clicks/impressions, with hiddenShare (fraction), level (ok < 5 %, warn 5–15 %, high > 15 %), the worst day and an optional daily table. Only searchType applies (dimension filters do not make sense here). Use to explain why top-queries totals do not add up to the summary, and before trusting query-level shares on small sites. / Cliques escondidos pela anonimização do Search Console.
Inputs: site (required), days, endDate, startDate, +2 more.
breakdown_by_pathBy subdomain and folderARead-onlyIdempotentInspect
Groups the property's pages by host (subdomain) and by the first depth path segments (1–4), e.g. "example.com/blog/*": pages per group, clicks, impressions, ctr, position, clickShare, comparison (prevClicks, clicksChange, clicksChangePct, positionChange) and the top 3 pages of each group. Sorted by clicks. Use for "which section drives traffic", "is the blog growing", "how is the /pt/ folder doing" and to compare subdomains. / Tráfego por subdomínio e pasta (profundidade 1–4).
Inputs: site (required), days, brand, depth, +10 more.
check_ai_accessAI crawler access checkARead-onlyIdempotentInspect
Checks whether AI crawlers can read one public web page and whether the page is set up to be cited. For the exact URL path it evaluates the domain's robots.txt for 8 AI robots (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended, Bingbot, CCBot, Applebot-Extended), each as allowed, blocked or no-rule (no rule for that robot or *, so allowed by default), or unknown when robots.txt could not be read; it checks for a valid /llms.txt (title, link count); and it reads the page's JSON-LD for citable types (Article, BlogPosting, FAQPage, HowTo…) and the fields that are missing (author Person with url, datePublished, dateModified, Organization.sameAs). Each part has a verdict (pass, warn, fail, info). Works without signing in and without a property: it fetches three public URLs of the site (the page, /robots.txt, /llms.txt) and stores nothing. Only public http/https addresses on the standard ports are accepted; private, local and internal addresses return invalid_argument. Use it to answer "can GPTBot / ClaudeBot / PerplexityBot read this page", "does this site have llms.txt" or "does this page have the structured data to be cited". It does not measure traffic or rankings. / Checa, sem login, se os robôs de IA podem ler uma página pública (robots.txt no caminho exato, llms.txt e JSON-LD de citação); não mede tráfego nem posição. Docs: https://organiqgeo.com/docs#check_ai_access
Inputs: url (required).
check_connectionConnection statusARead-onlyIdempotentInspect
Reports whether this request is authenticated and, if so, which Organiq account it uses (name, plan, how it authenticated), how many Search Console properties are available with their data coverage, and what is missing (no account, no properties, and per property GA4, Bing and branded terms) with the panel URL and the steps that resolve each gap. Without credentials it explains how to connect. Use it when a tool returned unauthorized/site_not_found or before a first analysis. / Diz se há conta, propriedades, plano e o que falta, com a URL para resolver.
Inputs: no named parameters.
detect_anomaliesDaily anomalies (weekday-robust)ARead-onlyIdempotentInspect
Flags days in the period whose clicks (or impressions, ctr, position) deviate from what the same weekday did in the previous baselineWeeks weeks (default 8): expected = median of those weekdays, scale = scaled MAD, zScore = (value − expected) / scale; anomaly when |z| >= threshold (sensitivity low 4, medium 3, high 2.5). Robust to outliers in the baseline and to the weekly cycle (weekends are compared with weekends). Each anomaly has direction (drop/spike; for position, drop = visibility loss), severity, deviationPct and the baseline size. Use for "did anything unusual happen", to date a drop before looking at causes (get_annotations), or to check a release day. / Dias anômalos comparados com o mesmo dia da semana nas semanas anteriores.
Inputs: site (required), days, brand, query, +9 more.
detect_change_pointsSustained level shifts (change points)ARead-onlyIdempotentInspect
Finds the dates where the property's clicks (or impressions) moved to a new sustained level — a step up or down that holds for several weeks, as after a Google update, a migration or a content launch — using a robust CUSUM on the weekly (default) or daily series. Each point has date, direction, before/after averages (4 observations each), change, changePct and how many following observations stayed on the new level. Isolated spikes are not change points (see detect_anomalies). Default period 52 weeks. Use to date a lasting drop or gain and then correlate with get_annotations. / Degraus sustentados na série (semanal ou diária), com antes × depois.
Inputs: site (required), days, brand, limit, +11 more.
find_decaying_contentDecaying contentARead-onlyIdempotentInspect
Pages (or queries) that lost clicks between a BASELINE and the RECENT period. Recent = days/startDate/endDate; baseline = compare (previous = window before, year = one year earlier) or explicit comparisonStartDate/comparisonEndDate (for slow decay compare with 6–12 months ago). Classifies the drop: severe > 50%, moderate 20–50%, mild < 20%; sorted by absolute clicks lost; pattern hints the diagnosis (position_slipped, impressions_collapsed, ctr_dropped, disappeared, mixed). Use for "which pages are dying" and refresh candidates. / Conteúdo em decaimento.
Inputs: site (required), days, brand, limit, +12 more.
find_internal_link_opportunitiesInternal link opportunitiesARead-onlyIdempotentInspect
Internal links to add, from the latest finished site audit: a target page that has a Search Console query at positions 4–20, and a source page of the same site whose text contains that query and does not link to the target yet. Each row has sourceUrl, targetUrl, query, snippet (up to 160 characters of the source text where the link fits), impressions (of the query on the target page, last 28 days) and position (average, lower is better). Ordered by impressions of the target; up to 3 sources per target and query. Page text is not stored, only the snippet. Use it to improve internal linking for pages already close to page one. / Links internos a criar: página de origem, destino, consulta, trecho, impressões e posição.
Inputs: site (required), limit, targetContains.
find_page_poaching_opportunitiesStriking distance (page poaching)ARead-onlyIdempotentInspect
Queries just outside the top (default positions 4–20) with the estimated click gain if they reached the CTR of the target position (default 3 → 18.6% benchmark, or the property's own CTR at that position when it has volume: see ctrSource). estimatedGain = max(0, round(impressions × (targetCtr − ctr))). Sorted by impressions (default) or by gain. Use for "what is close to page one / top 3". / Queries perto do topo com ganho estimado.
Inputs: site (required), days, sort, brand, +12 more.
forecast_trafficTraffic forecastARead-onlyIdempotentInspect
Projects the property's clicks (or impressions) for the next horizon weeks (default 12) or months (default 6) from the history in the period (default 364 days): aggregates the daily series, estimates a multiplicative seasonal index when >= 2 full cycles exist (otherwise 1.0, stated in seasonality), fits linear / logarithmic / exponential / power / polynomial trendlines and keeps the best adjusted R² (model=auto) or the one requested; forecast points carry baseline, low/high (±1.96 × residual sd, widening with the horizon), seasonalIndex and, with growthRate, a growth scenario (baseline × (1 + growthRate)); cvr + aov add revenue (= visits × cvr × aov). Returns an error when fewer than 8 full weeks / 6 full months exist. Use for "what should we expect next quarter", target setting and scenario planning; treat it as a trend extrapolation, not a promise. / Previsão semanal ou mensal com sazonalidade, trendline auto-selecionada, faixa e cenário de crescimento.
Inputs: site (required), aov, cvr, days, +13 more.
generate_seo_reportSEO report (markdown)ARead-onlyIdempotentInspect
One compact report for a property over the period (default 28 days, 7–180) with the comparison period: headline KPIs with change and year-over-year, top movers (queries and pages up/down), daily anomalies and sustained level shifts, Google updates and annotations, decaying pages, cannibalized queries, CTR quick wins, brand share, Core Web Vitals, indexing health, AI search (GA4 sessions from assistants, impressions in AI Overviews / AI Mode, AI-style query share), Bing, and up to three data-derived next actions. Parts without data (no GA4, no CrUX, no imports) or outside the plan are listed in skipped instead of failing. format=markdown (default) or json (the structured parts). Use for monthly client reports or a full status check in one call. / Relatório SEO completo em markdown (ou JSON) numa chamada.
Inputs: site (required), days, rows, brand, +9 more.
get_ai_trafficTraffic from AI assistants (GA4)ARead-onlyIdempotentInspect
Referral sessions from AI assistants (chatgpt.com, perplexity.ai, gemini, copilot, claude…) according to GA4 (dimension ai_source): per source (sessions, activeUsers, engagedSessions, keyEvents) for the period and the comparison, totals and daily series. site also accepts "all" for the whole account. A property without GA4 returns the error no_data with the panel URL where GA4 is connected (site="all" returns hasGa4=false and a setup note instead). Limitation: Search Console does not separate clicks from AI Overviews / AI Mode; only referral traffic is measurable. / Sessões vindas de IAs segundo o GA4.
Inputs: site (required), days, compare, endDate, +1 more.
get_annotationsAnnotationsBRead-onlyIdempotentInspect
Events annotated in the period for the property and globally: deploys, content changes, manual notes and Google algorithm updates (category "algo_update"). Use to correlate drops or gains with causes. Default: last 90 days. / Anotações e algo updates do período.
Inputs: site (required), days, endDate, startDate.
get_audit_issuePages affected by an audit issueARead-onlyIdempotentInspect
One issue code from the latest finished site audit: title, how to fix it, severity and the affected pages ordered by impressions of the last 28 days (url, HTTP status, depth, in sitemap, clicks, impressions). Codes come from get_site_audit (for example title_missing, broken_internal_link, noindex_with_clicks). Site-wide codes (robots_missing, sitemap_missing, llms_txt_missing, ai_bots_blocked, robots_blocks_audit) have no page list. Use it after get_site_audit to see which pages to fix for one issue. / Um problema da auditoria: título, correção e páginas afetadas por impressões.
Inputs: code (required), site (required), limit, language.
get_bing_performanceBing Webmaster performanceARead-onlyIdempotentInspect
Organic performance on Bing (Bing Webmaster Tools, weekly data) for the property: view=traffic gives weekly clicks/impressions with totals and change vs the previous same-length window; view=queries or view=pages gives the top keys with clicks, impressions, impression-weighted position, previous-period values and growth/decline sorting. Period is in whole weeks ending on the last synced Bing week (default 12 weeks). A property without Bing returns no_data with the panel URL where Bing is connected; hasBing in list_sites tells which properties have it. Use for "how do we do on Bing", Bing vs Google query overlap, Copilot-era visibility. / Bing: tráfego semanal, queries e páginas com comparação.
Inputs: site (required), sort, view, limit, +4 more.
get_branded_performanceBranded vs non-branded, dailyARead-onlyIdempotentInspect
Daily series of branded and non-branded traffic (clicks, impressions, ctr, position per group, plus brandedClickShare) with totals for the period and the comparison, using the property's branded_terms. brandedTermsConfigured=0 means no terms are set and everything counts as non-branded (set them in the "Integrações" block of the property in the Organiq panel; the response carries the URL). Use to separate brand demand from SEO work, to check whether a drop was brand or non-brand, and to track brand share over time. / Marca × sem marca por dia, com totais e comparação.
Inputs: site (required), days, brand, query, +8 more.
get_breakdownBrand split and position bandsARead-onlyIdempotentInspect
Splits the period's traffic into branded/nonBranded (by the property's branded_terms) and into position bands (1-3, 4-10, 11-20, 21+) with impressions and clicks per band, plus queryCount. Position of each query = impression-weighted average over the period. Without branded terms on the property everything counts as nonBranded and the response says where to set them. Use for "how much of our traffic is brand" and "how much sits on page 2". / Marca × sem marca e faixas de posição.
Inputs: site (required), days, brand, query, +6 more.
get_capabilitiesWhat Organiq providesARead-onlyIdempotentInspect
Returns a factual overview of this connector: what data it holds (Google Search Console synced daily into Organiq, plus GA4 referral sessions from AI assistants), the list of tools with when to use each, units, default periods, how to connect an account (OAuth or API key), rate limits and example questions. Works without signing in. Use it first when you do not know what this server can answer. / Visão geral factual do conector, sem login: dados, ferramentas, unidades, como conectar, limites.
Inputs: language.
get_core_web_vitalsCore Web Vitals (CrUX)ARead-onlyIdempotentInspect
Field Core Web Vitals of the property's origin (or a URL) from the Chrome UX Report history, weekly, per form factor (PHONE, DESKTOP): latest p75 of LCP, INP, CLS, FCP, TTFB with rating (good / needs_improvement / poor by Google's thresholds), share of good experiences, trend vs 4 weeks earlier, passesCoreWebVitals, alerts when a metric changed rating or worsened >= 20 %, and up to 26 weeks of history. CrUX only exists for origins with enough Chrome traffic; the response lists what is available. Use for "is the site fast enough for Google", regressions after a release, mobile vs desktop. / Core Web Vitals reais (CrUX) por semana e dispositivo, com tendência e alertas.
Inputs: site (required), weeks, formFactor, originOrUrl.
get_ctr_benchmarkGeneric CTR-by-position benchmarkARead-onlyIdempotentInspect
Returns the generic organic click-through-rate curve by Google position (1–20, fraction 0–1) used by score_opportunities and find_page_poaching_opportunities as the fallback when a property lacks its own volume, optionally interpolated for a fractional position. No account needed; no property data involved. Use it to estimate expected clicks for a position or to explain a CTR gap. / Curva genérica de CTR por posição, sem login.
Inputs: position, impressions.
get_ctr_curveOwn CTR curve vs benchmarkARead-onlyIdempotentInspect
The property's real CTR by position (bucket = round(position), 1–20, impression-weighted) compared with the generic benchmark (31.7% at position 1 … 18.6% at 3 … 2.0% at 10). deltaPoints in percentage points (negative = below expected: likely title/meta problem); reliable = bucket with enough impressions. Use to find where titles underperform. / Curva de CTR própria × benchmark.
Inputs: site (required), days, brand, query, +7 more.
get_genai_impressionsImpressions in AI Overviews / AI ModeARead-onlyIdempotentInspect
Daily impressions of the property in Google's generative AI features (AI Overviews and AI Mode) from the Search Console "Generative AI features" report, imported into Organiq (this report is not in the Search Analytics API and has no clicks). kind = all (default), text or multimodal. Returns totals for the period and the comparison with change, the daily series and the import coverage (firstDate, lastDate, importedAt). hasData=false when nothing was imported for the property. Requires the GEO add-on (error plan_limit otherwise). Use for GEO: "how visible are we inside AI Overviews", trend after content changes, share vs classic impressions (compare with get_site_summary). / Impressões na Visão geral de IA e no Modo IA (relatório importado), com série diária e comparação.
Inputs: site (required), days, kind, compare, +2 more.
get_indexing_requestsIndexing requestsARead-onlyIdempotentInspect
Lists the indexing requests made for the property (from request_indexing, the panel or the sitemap job), newest first: url, engine (indexnow / google), action, source (manual / sitemap / agent), status (queued, submitted, failed, skipped), queuedAt, submittedAt, httpStatus and error (the cause of a failed or skipped request; starts with google_not_eligible when the page has no JobPosting or BroadcastEvent structured data). Filter by status; days = how far back (default 7, max 365). Returns counts per status and per engine, plus the daily credit per route (indexnow and google: used, limit, left; null = no limit). Reads only Organiq data. A sent request is not a confirmation; the confirmed state comes from the inspection (get_indexing_tracker). Use after request_indexing to see what was sent or why a request failed. / Pedidos de indexação da propriedade, com status por motor e crédito do dia.
Inputs: site (required), days, limit, status.
get_indexing_trackerIndexing health (URL inspections)ARead-onlyIdempotentInspect
Indexing status of the property's inspected URLs (Search Console URL Inspection results stored by Organiq, plus the tracked_urls watch list): healthScore 0–100 (70 % indexed share + 30 % fresh-crawl share), indexed / not indexed counts, breakdown by coverageState and verdict, crawl freshness (fresh <= 30 days, aging, stale >= 120 days, never), alerts (deindexed since an earlier check, fetch errors, robots blocks, canonical mismatch, stale crawl, not indexed) and coverage over time by week of check. hasData=false means no inspection has been stored for this property yet (the inspection sync is not enabled for the account). The submissions field adds the last indexing request per URL (request_indexing: last submission time, state, cause, last inspection). Use for "are my pages indexed", "did Google drop a page", crawl staleness. / Saúde de indexação das URLs inspecionadas: nota 0–100, cobertura, frescor de crawl e alertas.
Inputs: site (required), alertLimit.
get_longtail_clustersHead / chunky middle / long tailARead-onlyIdempotentInspect
Splits the period's queries into head, chunky middle and long tail by word count (preset balanced: 1–2 / 3–4 / 5+ words; strict: 1 / 2–3 / 4+; loose: 1–3 / 4–5 / 6+), with queries, clicks, impressions, ctr, position, shares and top examples per tier, plus a Pareto view (share of clicks held by the top 10 % / 25 % / 50 % of queries). Use for "how dependent are we on a few head terms", "how much comes from long-tail", content-planning by intent length. / Cauda longa por nº de palavras e curva de Pareto.
Inputs: site (required), days, brand, query, +9 more.
get_page_performanceOne page over timeARead-onlyIdempotentInspect
Daily performance of ONE page (URL) of the property. Returns totals for the period and the comparison with change, the daily (or weekly) series and the top counterparts (queries bringing the page traffic). Exact match (case-insensitive for queries); when nothing matches, the error lists up to 5 candidates containing the text. / Série de uma página exata.
Inputs: page (required), site (required), days, brand, +10 more.
get_position_distributionPosition bands per dayARead-onlyIdempotentInspect
How the property's queries spread across position bands 1-3, 4-10, 11-20 and 21+ for each day (or week) of the period: number of queries, clicks, impressions and impression share per band. Each query's position for a day is its impression-weighted average that day. Also returns the period aggregate and the share shift between the first and the last week (sharePoints, percentage points). Use for "are we moving from page 2 to page 1", "how much visibility sits beyond position 10", or to see when a band changed. / Faixas de posição por dia ou semana, com deslocamento entre a primeira e a última semana.
Inputs: site (required), days, brand, query, +7 more.
get_query_performanceOne query over timeARead-onlyIdempotentInspect
Daily performance of ONE search query on the property (optionally on one page). Returns totals for the period and the comparison with change, the daily (or weekly) series and the top counterparts (pages ranking for the query). Exact match (case-insensitive for queries); when nothing matches, the error lists up to 5 candidates containing the text. / Série de uma query exata.
Inputs: site (required), query (required), days, page, +10 more.
get_query_shape_trendQuery shape share over timeARead-onlyIdempotentInspect
Weekly share of impressions (or clicks) per query shape (branded, question, comparison, transactional, local, longtail, head, other) and of "AI-style" queries over the period (default 12 weeks), with sharePointsChange = last weeks minus first weeks in percentage points. Weeks are keyed by Monday; incomplete first/last weeks are listed in partialWeeks. Use to see whether questions / conversational queries are growing, i.e. demand shifting toward AI-style searches. / Tendência semanal da participação de cada formato de query, inclusive "estilo IA".
Inputs: site (required), days, brand, query, +7 more.
get_ranking_changesRanking changes between periodsARead-onlyIdempotentInspect
Classifies each query (or page) of the property by what happened between the comparison period and the current one: new (appeared), lost (disappeared), improved (position better by >= minPositionChange), declined (worse) or stable. Rows carry clicks/impressions/ctr/position for both periods, positionChange (negative = improved) and clicksChange; summary counts every status plus clicks gained from new and lost keys. Sorted by impressions then by size of the move. Use for "what did we gain or lose in rankings", "which queries fell off", "new queries this month". / Queries ou páginas novas, perdidas, que subiram ou caíram entre dois períodos.
Inputs: site (required), days, brand, limit, +12 more.
get_site_auditSite auditARead-onlyIdempotentInspect
Result of the latest finished crawl audit of the property's own site (HTML only, no JavaScript): audit date, pages crawled, the plan's per-audit page limit and whether the crawl was cut by it, two health scores (0–100) with the formula written out (page health: share of crawled pages with no error; traffic health: share of Search Console impressions of the last 28 days that land on pages with no error), pages counted per severity (error, warning, notice), issues sorted by impressions of the affected pages (code, severity, title, fix, pages, impressions, clicks), site-wide issues (robots.txt, sitemap, llms.txt, AI bots) and the health trend over the previous audits. Without a finished audit it states the state of the last one and points to request_site_audit. Use it for "how healthy is the site" or "what should I fix first"; get_audit_issue lists the pages of one issue. / Última auditoria concluída do site: nota por páginas e por tráfego com a fórmula, problemas por impressões afetadas, problemas do site inteiro e tendência.
Inputs: site (required), limit, language.
get_site_summaryProperty summaryARead-onlyIdempotentInspect
Totals of clicks, impressions, CTR and average position for one property over the period, with the comparison period and the change (absolute, Pct as fraction, ctrPoints in percentage points, position difference where negative means improvement). Accepts all filters (country, device, brand, page, query). Start here for "how is site X doing". / Resumo da propriedade com comparação.
Inputs: site (required), days, brand, query, +7 more.
get_timeseriesTime seriesARead-onlyIdempotentInspect
Clicks, impressions, CTR and position per day, week (Monday as key) or month (yyyy-mm) over the period, with filters. Use for trend, seasonality and to locate the date of a drop. Days without data are omitted. / Série temporal por dia, semana ou mês.
Inputs: site (required), days, brand, query, +7 more.
get_weekly_digestWeekly digestARead-onlyIdempotentInspect
Short weekly digest for a property: the last 7 synced days vs the 7 before (and year-over-year), top 3 queries/pages up and down, anomalies of the week, Google updates and annotations, quick wins, technical alerts (Core Web Vitals, indexing), AI search lines and three next actions. Computed live from the synced data; when the account's weekly report job has run, storedReport carries the saved report's KPIs and actions (the same the e-mail/Slack digest sent) and alerts lists the alerts raised in the week. endDate moves the week (default: last synced date). Use for "what changed this week", Monday stand-ups, a client's weekly update. / Resumo da semana com movers, anomalias, alertas e 3 ações.
Inputs: site (required), brand, query, device, +5 more.
list_ga4_propertiesGA4 properties of the Google accountARead-onlyIdempotentInspect
Lists the Google Analytics 4 properties the connected Google account can see (Analytics Admin API accountSummaries.list): id (numeric, the value set_ga4_property takes), displayName and the GA4 account name, sorted by account. Needs an active Google connection in the Organiq account that granted analytics.readonly; otherwise no_data with reason scope_missing / no_connection / token_revoked and the step that fixes it. Use it before set_ga4_property to find the property id, or when the user does not know their GA4 property id. Guide: https://organiqgeo.com/connect/ga4. / Lista as propriedades GA4 da conta Google conectada, para escolher o id em set_ga4_property.
Inputs: no named parameters.
list_sitemapsSitemapsARead-onlyIdempotentInspect
Sitemaps known to Search Console for the property: path, lastSubmitted, lastDownloaded, isPending, errors, warnings and contents per type (web, image, video, news: submitted URL counts). Search Console no longer reports indexed counts per sitemap through the API, so indexed is usually 0 — use get_indexing_tracker for indexing. Use to confirm Google is fetching the sitemap, spot errors/warnings and count submitted URLs. / Sitemaps da propriedade com status de download, erros e URLs enviadas.
Inputs: site (required).
list_sitesProperties in the accountARead-onlyIdempotentInspect
Lists the Search Console properties synced for the signed-in account: id, siteUrl (Search Console format), displayName, tags, branded_terms (used by the brand filter), whether GA4/Bing are mapped and the data coverage (dataFrom/dataTo, web search). Use it first when you do not know the exact name of a site or need the date range available. Default: visible properties only. / Propriedades da conta com cobertura de dados.
Inputs: includeHidden.
list_url_inspectionsURL inspection resultsARead-onlyIdempotentInspect
Latest stored URL Inspection result per URL of the property: verdict, coverageState, indexingState, robotsState, pageFetchState, Google vs user canonical, lastCrawlTime, crawledAs, mobileVerdict, checkedAt, whether the URL is on the tracked list and lastSubmittedAt (last indexing request made with request_indexing, null if none). Filter by status (indexed / not_indexed) or by URL text. hasData=false when no inspection is stored yet. Use after get_indexing_tracker to see specific URLs, or to check one URL's state. / Resultado da inspeção de cada URL (indexada?, canonical, último crawl).
Inputs: site (required), limit, status, urlContains.
query_countriesBy countryARead-onlyIdempotentInspect
Countries (ISO-3166-1 alpha-3, lowercase, e.g. bra) of one property over the period. Each row has clicks, impressions, ctr, position for the period and, with a comparison, prevClicks/prevImpressions/prevCtr/prevPosition plus clicksChange/clicksChangePct/positionChange (keys present in only one period show zeros in the other). sort: clicks (default), impressions, ctr, position (lowest first), growth (largest click gain vs comparison first) or decline (largest loss first). For ctr/position use minImpressions >= 20 to avoid noise. / Por país.
Inputs: site (required), days, sort, brand, +10 more.
query_devicesBy deviceARead-onlyIdempotentInspect
Devices (MOBILE, DESKTOP, TABLET) of one property over the period. Each row has clicks, impressions, ctr, position for the period and, with a comparison, prevClicks/prevImpressions/prevCtr/prevPosition plus clicksChange/clicksChangePct/positionChange (keys present in only one period show zeros in the other). sort: clicks (default), impressions, ctr, position (lowest first), growth (largest click gain vs comparison first) or decline (largest loss first). For ctr/position use minImpressions >= 20 to avoid noise. / Por dispositivo.
Inputs: site (required), days, sort, brand, +10 more.
query_top_pagesTop pagesARead-onlyIdempotentInspect
Pages (URLs) of one property over the period, aggregated and sorted. Use for best/worst pages and pages that gained or lost clicks. Each row has clicks, impressions, ctr, position for the period and, with a comparison, prevClicks/prevImpressions/prevCtr/prevPosition plus clicksChange/clicksChangePct/positionChange (keys present in only one period show zeros in the other). sort: clicks (default), impressions, ctr, position (lowest first), growth (largest click gain vs comparison first) or decline (largest loss first). For ctr/position use minImpressions >= 20 to avoid noise. / Páginas da propriedade, agregadas e ordenadas.
Inputs: site (required), days, sort, brand, +10 more.
query_top_queriesTop queriesARead-onlyIdempotentInspect
Search queries of one property over the period, aggregated and sorted. Use for "what people search to find us", growth/decline lists and ranking changes. Each row has clicks, impressions, ctr, position for the period and, with a comparison, prevClicks/prevImpressions/prevCtr/prevPosition plus clicksChange/clicksChangePct/positionChange (keys present in only one period show zeros in the other). sort: clicks (default), impressions, ctr, position (lowest first), growth (largest click gain vs comparison first) or decline (largest loss first). For ctr/position use minImpressions >= 20 to avoid noise. / Queries da propriedade, agregadas e ordenadas.
Inputs: site (required), days, sort, brand, +10 more.
request_indexingRequest indexing of URLsAIdempotentInspect
Queues up to 100 URLs of one property for submission to search engines, by two routes: IndexNow (Bing, Yandex, Naver, Seznam, Yep; needs the IndexNow key set for the property) and Google through the Indexing API (optional per property). Google route (Indexing API) only sends pages with JobPosting or BroadcastEvent structured data, as Google requires; other URLs are checked at send time, not here: get_indexing_requests later shows them skipped, error starting google_not_eligible, and go through IndexNow when configured. Parameters: urls (absolute URLs of the property), action update (default) or delete, engines (indexnow and/or google; default: the configured routes). Returns queued (url + engine), skipped with a reason per URL (invalid_url, outside_property, duplicate_24h, daily_limit_indexnow, daily_limit_google, google_not_allowed_by_plan, google_not_configured, indexnow_not_configured) and creditsLeft ({indexnow, google}: URLs still allowed today on each route; null = no daily limit on that route). A submission is a request, not a confirmation: see get_indexing_requests and list_url_inspections. Writes only to Organiq (the request queue) and sends the URLs to the engines; never changes Search Console. Needs mcp:write. Errors: indexing_not_configured with the panel step; plan_limit only when no requested engine is allowed by the plan. A spent daily credit is not an error: the URLs come back in skipped (daily_limit_*). / Envia até 100 URLs para indexação (IndexNow e, opcional, Google Indexing API); grava só no Organiq e não altera o Search Console.
Inputs: site (required), urls (required), action, engines.
request_site_auditRequest a site auditAIdempotentInspect
Queues a crawl audit of the property's own site in Organiq (HTML pages inside the verified property, robots.txt respected). Answers status "queued", or "not_queued" with reason "already_open" (an audit is queued or running) or "recent" (the last audit finished less than 24 hours ago), with the date of the last audit. The audit finishes within minutes to some hours depending on site size; read the result with get_site_audit. Writes only to Organiq, never to the audited site, Search Console, GA4 or Bing. Needs the write scope (mcp:write). Use it when get_site_audit reports no audit yet or the user fixed issues and wants a new reading. / Põe uma auditoria do site na fila; recusa se já há uma aberta ou se a última tem menos de 24 h.
Inputs: site (required).
score_opportunitiesOpportunity score (CTR gap)ARead-onlyIdempotentInspect
Queries between minPosition and maxPosition whose CTR is below the expected CTR for their position. expectedCtr comes from the property's own curve (ctrSource "own", when the bucket has volume) or from the benchmark; ctrGap = expected − ctr (fraction); lostClicks = impressions × gap; score 0–100 log-normalized by the largest lostClicks (level high >= 80, medium >= 60). Use for title/meta-description quick wins. / Oportunidades por CTR abaixo do esperado.
Inputs: site (required), days, brand, limit, +10 more.
set_bing_keyStore the Bing Webmaster API keyADestructiveIdempotentInspect
Tests the Bing Webmaster Tools API key against Bing (GetUserSites) and, only if Bing accepts it, stores it for the Organiq account (one key per account; it serves every property with a Bing site set by set_bing_site). The key is generated by the user in Bing Webmaster Tools under Settings → API access ("Configurações → Acesso à API") and pasted in the chat; it is stored encrypted, never returned by any tool and not logged. Format: 16–128 letters, digits, "-" or "_". Bing refuses the key → bing_key_invalid and the previously stored key, if any, stays; Bing down or slow → upstream_unavailable and nothing is stored (retry in a few minutes). Only an owner or admin of the account can store it (insufficient_scope otherwise). Returns { set, setAt, bingSites }: bingSites are the site URLs Bing lists for the key, to check the value given to set_bing_site. Needs the write scope (mcp:write). Use it after set_bing_site, or when get_bing_performance / check_connection report the key missing. Guide: https://organiqgeo.com/connect/bing. / Testa a chave da API do Bing no próprio Bing e só grava, cifrada, se ele aceitar; chave recusada não substitui a anterior.
Inputs: key (required).
set_bing_siteSet the Bing Webmaster siteADestructiveIdempotentInspect
Sets the site URL registered in Bing Webmaster Tools for one Search Console property in Organiq (same rule as the panel): https, no query/fragment, and on the property's own domain (an sc-domain property accepts the domain and its subdomains; a URL-prefix property requires the same host under its path); null clears it. Returns the property settings and whether the account's Bing API key is set (set_bing_key). When the value changes, the Bing data already synced is deleted and the next daily sync rebuilds it; get_bing_performance answers after a sync with both the site and the key in place. Needs the write scope (mcp:write). Use it when check_connection lists no_bing or the user asks to connect Bing. Guide: https://organiqgeo.com/connect/bing. / Grava a URL do site no Bing Webmaster Tools para a propriedade; precisa também da chave da conta (set_bing_key).
Inputs: site (required), bingSiteUrl (required).
set_branded_termsSet the branded termsADestructiveIdempotentInspect
Replaces the branded terms of one Search Console property in Organiq (the list used by the brand filter, get_breakdown, get_branded_performance and the branded shape of analyze_query_shapes): brand and product names as people type them, up to 20 terms of 2–40 characters, lower-cased and de-duplicated; a query counts as branded when it contains one of them. The whole list is replaced (send the full list; [] clears). Takes effect immediately on the next read (no sync needed). Needs the write scope (mcp:write). Use it when check_connection lists no_branded_terms or brand=branded was rejected. / Substitui os termos de marca da propriedade (até 20); vale na hora.
Inputs: site (required), terms (required).
set_ga4_propertyLink a GA4 propertyADestructiveIdempotentInspect
Links a Google Analytics 4 property to one Search Console property in Organiq (the same setting as the panel's "Integrações" block): ga4PropertyId is the numeric id from list_ga4_properties ("123456789" or "properties/123456789"); null unlinks. Returns the property settings. When the value changes, the GA4 data already synced from the previous property is deleted and the next daily sync rebuilds the history from the new one (Search Console data is untouched); get_ai_traffic answers after that sync. Needs the write scope (mcp:write). Use it when check_connection lists no_ga4 or the user asks to connect GA4. Guide: https://organiqgeo.com/connect/ga4. / Liga a propriedade GA4 à propriedade do Search Console; trocar apaga o GA4 já sincronizado e o sync refaz.
Inputs: site (required), ga4PropertyId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
SEO and AI visibility: site audits, Search Console, Analytics, Bing, rank and ChatGPT tracking.
SEO analysis for sites you own: Google Search Console, GA4, PageSpeed, and full site audits.
SEO and AI search visibility: Search Console data, keyword research, AI visibility audits and fixes.
SEO research and tracking: keywords, SERPs, backlinks, site audits, Search Console and GA4.
1
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides analytics and SEO insights from Google Analytics 4 and Google Search Console. Supports querying traffic, engagement, conversions, search performance, URL inspection, and sitemap management.8 npmMIT
- AlicenseCqualityDmaintenanceAn SEO analysis MCP server integrating Google Search Console, Bing Webmaster Tools, and GA4 with custom grain analysis tools for content decay, traffic drops, CTR benchmarking, and actionable recommendations.1001MIT
- AlicenseNot gradedqualityCmaintenanceConnects Claude, Cursor and other AI assistants to Google's search performance data, URL inspection and sitemaps on the user's own machine. On top of the raw data it returns ready-made analysis: quick-win keywords, weak click-through, keyword cannibalization, declining pages and sitemap indexing audits.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables querying Google Search Console and Google Analytics 4 through natural language, with tools for SEO analysis like anomaly detection, cannibalization detection, and opportunity scoring.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.