timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Search Console and GA4 analysis (read-only Google): queries, decay, cannibalization, AI traffic.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0 |
| 5. 登记日期 | 2026-11-03 |
用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。
质量: 基础检查通过 4/4 项(仅展示,不用于排序)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Organiq GEO。按照 https://mcp.popnx.com/i/organiqgeo-organiq.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 4/4 项检查 · 你的提问会经过开发者的服务器(organiqgeo.com) · ✓ 命令已检查 2026年11月20日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Organiq GEOhttps://organiqgeo.com/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsOrganiq GEO
用 Organiq GEO 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Organiq GEO,或回答中出现 Organiq GEO 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Organiq GEOhttps://organiqgeo.com/mcp开启新聊天,输入前先从插件列表中选择 Organiq GEO
用 Organiq GEO 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Organiq GEO,或回答中出现 Organiq GEO 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user organiq https://organiqgeo.com/mcp应能看到 Organiq GEO 在列表中并显示已连接
用 Organiq GEO 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Organiq GEO,或回答中出现 Organiq GEO 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 Organiq GEO 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Organiq GEO,或回答中出现 Organiq GEO 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 Organiq GEO 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Organiq GEO,或回答中出现 Organiq GEO 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://organiqgeo.com/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user organiq https://organiqgeo.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"organiq": {
"url": "https://organiqgeo.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"organiq": {
"type": "http",
"url": "https://organiqgeo.com/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
工具名称和描述与服务器在 2026年11月17日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
get_capabilitiesReturns 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 l
get_ctr_benchmarkReturns 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
check_connectionReports 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 br
check_ai_accessChecks 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), e
list_sitesLists 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 kn
get_site_summaryTotals 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, dev
query_top_queriesSearch 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/prev
query_top_pagesPages (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 clicksCh
query_countriesCountries (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 prese
query_devicesDevices (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 per
get_timeseriesClicks, 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.
get_breakdownSplits 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
get_annotationsEvents 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.
get_ai_trafficReferral 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" f
get_ctr_curveThe 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 = bucke
find_decaying_contentPages (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). C
analyze_cannibalizationQueries 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
score_opportunitiesQueries 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 ×
find_page_poaching_opportunitiesQueries 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
get_ranking_changesClassifies 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 b
get_position_distributionHow 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 t
get_branded_performanceDaily 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-b
breakdown_by_pathGroups 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
get_query_performanceDaily 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 noth
get_page_performanceDaily 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 erro
get_longtail_clustersSplits 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
analyze_sampling_impactHow 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
analyze_query_shapesClassifies 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 t
get_query_shape_trendWeekly 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
detect_anomaliesFlags 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| >= threshol
detect_change_pointsFinds 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 d
forecast_trafficProjects 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, st
get_core_web_vitalsField 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
get_indexing_trackerIndexing 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, cra
list_url_inspectionsLatest 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_indexingQueues 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 page
get_indexing_requestsLists 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 er
list_sitemapsSitemaps 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
get_bing_performanceOrganic 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 po
get_genai_impressionsDaily 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 multimo
generate_seo_reportOne 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,
get_weekly_digestShort 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 action
list_ga4_propertiesLists 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 acco
set_ga4_propertyLinks 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
set_bing_siteSets 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 sa
set_bing_keyTests 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
set_branded_termsReplaces 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-ca
get_site_auditResult 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 p
get_audit_issueOne 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_inter
find_internal_link_opportunitiesInternal 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 (u
request_site_auditQueues 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
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过域名 organiqgeo.com 验证(注册中心会核实域名所有权)
代码最后更新于14天前
不适用:由 organiqgeo.com 的所有者自己运行的云端服务器,你不会运行仓库里的代码
在 395 毫秒内响应(HTTP 200)
无需登录
已读取 51 个工具描述,未发现针对 AI 的隐藏指令
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/organiqgeo-organiq)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于14天前,最新版本(0.6.0)于17天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Official Exa MCP for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 Organiq GEO | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 4/4 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | Apache-2.0 | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Site · Docs · Guides: Claude, Claude Code, Cursor · Privacy · Terms · Support · Security
Português abaixo
Organiq (organiqgeo.com) is the Google Search Console connector for AI agents: Claude, ChatGPT, Cursor and Gemini CLI connect with one URL and a read-only Google sign-in and get Search Console, GA4 AI-assistant sessions and Bing in one MCP server, with 47 tools and history beyond Google's 16 months. Free plan; paid from US$ 9/month. Operated by Youssef Pizolotto Umar.
This repository is the Claude Code plugin: eight skills that teach Claude how to analyse your own data through the connector, plus the connector entry (.mcp.json).
| Connector | https://organiqgeo.com/mcp (remote, Streamable HTTP) |
| Tools | 47: 42 read tools and 5 tools that write only to Organiq; 4 work before sign-in (get_capabilities, get_ctr_benchmark, check_connection, check_ai_access) |
| Google access | Read-only. The read tools only read; the 5 tools that write change only Organiq data (linked GA4, Bing site and key, brand terms, indexing requests) and need the mcp:write scope. Nothing is written to Search Console, GA4 or Bing |
| Authentication | OAuth 2.1 with Google sign-in; API key for clients without OAuth |
| Data | Search Console, GA4 sessions from ChatGPT, Perplexity, Gemini, Copilot and Claude, Bing Webmaster, Core Web Vitals |
| Needs | A site verified in Google Search Console. The Google sign-in creates the Organiq account and imports the properties; the dashboard is https://app.organiqgeo.com |
| License | Apache-2.0 |
Source of each exception (one link per cell, read on October 30, 2026; the optimization-cycle one, on November 5, 2026): https://organiqgeo.com/compare
Claude Code (plugin, includes the skills):
claude plugin marketplace add organiqgeo/organiq-plugin
claude plugin install organiq@organiq
Restart Claude Code (or run /reload-plugins), then /mcp → organiq → Authenticate and sign in with Google. Connector only, without the skills: claude mcp add --transport http organiq https://organiqgeo.com/mcp.
Claude (claude.ai): Settings → Connectors → Add custom connector → name Organiq, URL https://organiqgeo.com/mcp, leave Client ID and secret empty → Add → Connect → sign in with Google → Allow.
Cursor: add this under mcpServers in ~/.cursor/mcp.json (or .cursor/mcp.json in the project), then Settings → MCP → enable organiq and approve the sign-in window:
{ "mcpServers": { "organiq": { "url": "https://organiqgeo.com/mcp" } } }
Step-by-step guides, also for ChatGPT and Gemini CLI: https://organiqgeo.com/docs.
get_capabilities, get_ctr_benchmark, check_connection, check_ai_access, list_sitesget_site_summary, get_timeseries, query_top_queries, query_top_pages, query_countries, query_devices, get_breakdown, breakdown_by_path, get_query_performance, get_page_performance, get_ranking_changes, get_position_distribution, get_branded_performance, get_longtail_clusters, get_annotationsget_ctr_curve, find_decaying_content, analyze_cannibalization, score_opportunities, find_page_poaching_opportunitiesdetect_anomalies, detect_change_points, forecast_trafficget_ai_traffic, get_genai_impressions, analyze_query_shapes, get_query_shape_trend, analyze_sampling_impactget_core_web_vitals, get_indexing_tracker, get_indexing_requests, list_url_inspections, list_sitemaps, get_bing_performancegenerate_seo_report, get_weekly_digestrequest_indexing sends URLs to IndexNow and, when the property enables it, to the Google Indexing API, only for pages with JobPosting or BroadcastEvent markup (the use Google documents; other URLs are skipped there and go through IndexNow), and records the request in Organiq; it does not change Search Console. get_indexing_requests (read) shows the status per URL and engine.list_ga4_properties, set_ga4_property, set_bing_site, set_bing_key, set_branded_terms. They link GA4, set the Bing site and API key and replace the brand terms; list_ga4_properties only lists. The Bing API key is generated by you in the Bing portal and pasted in the chat. The sign-in asks for mcp:read mcp:write; if you connected before, remove the connector and add it again.Every answer states the property, the period and the comparison used. CTR is a fraction (0.052 = 5.2%) and position is an impression-weighted average (lower is better).
| Skill | Use when |
|---|---|
quick-wins | queries with CTR below expected, striking distance, what to optimise first |
content-decay | pages losing clicks, refresh candidates, why a page dropped |
cannibalization | several URLs ranking for the same query |
weekly-report | weekly/monthly status for a site or client |
ai-traffic | sessions from ChatGPT, Perplexity, Gemini, Copilot, Claude; conversational queries |
geo-audit | monthly GEO report: AI referrals per source, question-style queries, AI Overviews hypothesis, 3 actions |
site-audit | one-pass audit of a property: headline, trajectory, mix, movers, decay, cannibalization, quick wins |
optimization-cycle | inside the site's repository: judges the previous changes, edits up to three pages and one new page from the data, verifies and logs them in .organiq/cycle.md |
The same skills are published for any agent at https://organiqgeo.com/.well-known/agent-skills/index.json.
claude plugin validate /path/to/organiq-plugin
claude plugin list # organiq@organiq enabled claude mcp list # organiq … Connected (after /mcp → Authenticate)
In a session, /mcp shows the organiq server with 47 tools (42 read, 5 write to Organiq), and typing "quick wins for example.com" loads the quick-wins skill.
The skills send only tool arguments (property name, dates, filters) to the Organiq server. The server returns aggregated Search Console and GA4 figures for properties in your own account, and never receives the conversation. Nothing is written to Google or Bing; the tools that write change only Organiq data. Disconnecting in the Google account settings revokes access.
Privacy · Terms · Support · Security · Docs
Organiq is operated by Youssef Pizolotto Umar, Brazil. Contact: youssefpmat@gmail.com. Contracting party and billing details are in the Terms. License: Apache-2.0.
Site · Docs · Guias: Claude, Claude Code, Cursor · Privacidade · Termos · Suporte · [Segurança](http