Statable Analytics

Statable Analytics — веб-аналитика без cookie с хостингом в ЕС

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

  • Строить агрегаты, временные ряды и топ-N по метрикам и измерениям
  • Смотреть топ страниц, источников трафика, стран и целей
  • Отслеживать живых посетителей и отчёты по воронкам
  • Создавать и настраивать сайты, цели и воронки
  • Управлять фильтрами сайта и параметрами трекинга

Какие данные видит

OAuth 2.1 с PKCE или API-ключ; ассистент видит только сайты, выбранные пользователем при авторизации.

Нужен ли аккаунт

Не нужен: сервер работает без входа

Statable Analytics отдаёт данные о посетителях сайта без использования cookie: страницы, источники трафика, страны, устройства, цели и воронки, живые посетители. 25 инструментов включают гибкий запрос агрегатов по любой метрике и измерению, а также настройку сайтов, целей и фильтров прямо из чата. Числа возвращаются в часовом поясе сайта, ничего не удаляется.

Как подключить

Как подключить Statable Analytics к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://analytics--statable.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить Statable Analytics к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://analytics--statable.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить Statable Analytics к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://analytics--statable.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (25)

Технические названия из tools/list. Нужны только разработчикам.

create_siteAdd a site to this account and get back its id and tracking code. Response: {"site_id":123,"name":"https://example.com","timezone":"Europe/Amsterdam",...}. The url must include the scheme. A url this account already has is REFUSED (site_exists) rather than returned — two sites collecting the same traffic is worse than an error. Retrying with the same arguments replays the first result instead of creating a second site. Follow with get_tracking_snippet to obtain the script tag to install.
update_siteChange a site's url, timezone or week start. Omitted fields are left alone. Returns the updated site. Changing the url to one this account already has is refused (site_exists).
list_goalsThe goals CONFIGURED on a site — what it measures, not how those goals performed. Use top_goals for conversion numbers. Response: {"goals":[{"id":7,"name":"Signup","event_name":"Signup"|null,"path":"/thanks"|null,"operator":"e|b|c","scroll_depth":N|null}]}.
create_goalAdd a goal to a site. A goal is EITHER a custom event (event_name), OR a page (path with operator), OR a scroll depth — give one of the three, not several. operator: "e" exact, "b" begins with, "c" contains. A duplicate name is refused (goal_exists).
update_goalReplace a goal's definition. Send the whole goal, not just the changed fields — omitted fields are cleared, not kept.
create_funnelAdd a funnel: an ordered list of 2+ steps. Each step is one of {"type":"page","value":"/pricing"}, {"type":"event","value":"Signup"}, {"type":"entry_page"|"exit_page","value":"/"}. An exit_page step must be last. scope "visitor" (default) or "session". A duplicate name is refused (funnel_exists). Read the result with funnel_report.
update_funnelReplace a funnel's definition. Send the whole funnel including every step — omitted steps are removed, not kept.
get_tracking_settingsWhat the installed script actually does: which tracking features are on, which exist, and what each costs in bytes. Response: {"site_id":123,"version":N,"bundle":"...","enabled":["hash","outbound"],"features":[{"id":"outbound","label":"...","enabled":true,"locked":false,"default":false,"requires":[...],"size_br":123}]}. Locked features cannot be changed; `requires` lists features that must be on for this one to work. Needs the same access as changing them (see update_tracking_settings).
update_tracking_settingsSet which tracking features the site's script includes. REPLACES the whole selection: send every feature you want enabled, not just the new one — anything omitted is turned off. Call get_tracking_settings first for the valid ids. Rebuilds and republishes the script, so the change reaches visitors after the CDN cache clears.
get_subscriptionThe account's plan state — not a site's. Response: {"status":"trialing"|"active"|"past_due"|"expired"|"trial_expired"|"none","is_trial":true,"ends_at":"RFC3339","only_hobby":false}. ends_at is when the CURRENT state stops being true (trial end while trialing, period end otherwise) and is omitted when unknown. status "none" with only_hobby true means a free account, not a missing one. Takes no arguments.
get_site_filtersWho gets counted on a site, and who may look at the stats. Response: {"site_id":123,"hostnames":{"allowed":[],"blocked":[]},"blocked_ips":["1.2.3.4"],"countries":{"allowed":[{"code":"UA","created_at":"RFC3339"}],"blocked":[]},"public_dashboard":false}. An empty allowed list means "no restriction", not "nothing allowed". public_dashboard true means the stats are readable by anyone with the link.
update_site_filtersChange who gets counted, and who may look. Send only the sections you want to change — an omitted section is left untouched. A section you DO send replaces that setting entirely: {"countries":{"blocked":["RU"]}} also clears the country allow list, and {"blocked_ips":[]} empties the blocklist. Read the current state with get_site_filters and send it back with your edit applied. Filtering takes effect on new traffic; it does not remove data already collected. Answers with the resulting state plus "updated":["hostnames",...] naming what changed.
get_tracking_snippetThe script tag to install on a site, and the url it loads. Response: {"site_id":123,"type":"default","script_url":"https://...","snippet":"<script ...></script>"}. Install snippet verbatim; do not rebuild a tag from script_url. A hobby site's snippet also carries data-id, which is the only place the counter in its bundle reads the site id. Read-only: it reports the code, it does not install or verify anything.
list_sitesList the sites this API key can read. Response: {"sites":[{"site_id":123,"name":"<as entered by the owner — often a full URL like https://example.com/>","hash":"07k1eD84d2","timezone":"Europe/Amsterdam","hobby":false,"stats_start_date":"YYYY-MM-DD"|null,"created_at":"RFC3339"}]}. hobby=true is a free-plan site: it counts only through the bundled /t/ script get_tracking_snippet returns, so install that snippet verbatim. Use site_id with the other tools. With date_range each site also carries metrics NESTED under stats.metrics (never flat on the site object). Units: visit_duration = average seconds per visit; bounce_rate = percent 0-100; views_per_visit = pageviews/visits ratio; visitors/pageviews/visits = counts. Stats period boundaries are server-time approximations; use query_stats for timezone-exact numbers.
query_statsRun a read-only analytics query for one site: aggregate totals, a time series, or a top-N breakdown. Returns {"results":[{"dimensions":{...omitted for aggregates},"metrics":{...}}]}. All dates and time buckets are in the site's own timezone (see list_sites .timezone). The event:name breakdown lists custom events (data-statable-event); its `events` metric is the raw event count. The event:goal breakdown lists the site's configured goals with `visitors` (converters), `events` (conversions) and `conversion_rate` (percent). `events`/`conversion_rate` are breakdown-only (rejected on aggregate/time-series or a dimension that doesn't compute them). Units: visit_duration = average seconds per visit; bounce_rate = percent 0-100; views_per_visit = pageviews/visits ratio; visitors/pageviews/visits = counts.
top_pagesTop pages by visitors for a site. Returns {"results":[{"dimensions":{"event:page":"/path"},"metrics":{"pageviews":N,"visitors":N}}]}.
top_sourcesTop traffic sources by visitors for a site. Returns {"results":[{"dimensions":{"visit:source":"Google"},"metrics":{"visitors":N,"bounce_rate":percent0to100}}]}.
top_countriesTop countries by visitors for a site. Returns {"results":[{"dimensions":{"visit:country":"US"},"labels":{"visit:country":"United States"},"metrics":{"visitors":N}}]} — the dimension value is the ISO alpha-2 code (drops straight into a country filter); the display name is in labels.
top_custom_eventsTop custom events (data-statable-event) by count for a site — pageview/engagement excluded. Returns {"results":[{"dimensions":{"event:name":"Signup"},"metrics":{"events":N,"visitors":N}}]}, where events is the raw occurrence count and visitors is unique users who triggered it.
top_goalsThe site's configured goals ranked by conversions. Returns {"results":[{"dimensions":{"event:goal":"Signup"},"metrics":{"visitors":N,"events":N,"conversion_rate":percent0to100}}]}, where visitors is unique converters, events is total conversions, and conversion_rate is visitors as a percent of all visitors in the period.
list_funnelsList the conversion funnels configured for a site (discovery — get a funnel_id for funnel_report). Returns {"funnels":[{"id":45,"name":"Signup flow","scope":"visitor","steps_count":3}]}.
list_prop_keysList the custom-property keys a site has recorded (with the event each belongs to) — discovery for the event:props:<key> breakdown in query_stats. Returns {"props":[{"key":"plan","event":"Signup","count":N,"first_seen":"RFC3339"}]}.
funnel_reportRun a saved conversion funnel and return its per-step result (NON-tabular). Returns {"funnel":{"id","name","scope"},"entering":N,"all_visitors":N,"steps":[{"index":0,"name":"Visited /pricing","kind":"page","visitors":N,"conversion_rate":percent0to100,"dropoff":N}, ...]}. steps are ORDERED; conversion_rate is cumulative vs the first step (entering), NOT step-to-step; dropoff is visitors lost vs the previous step. Get funnel_id from list_funnels first.
current_visitorsRealtime count of unique visitors active in the last 5 minutes for a site. Returns {"site_id":123,"visitors":N}.
visitors_over_timeDaily visitors and pageviews time series for a site, in the site's own timezone. Returns {"results":[{"dimensions":{"time:day":"YYYY-MM-DD"},"metrics":{"visitors":N,"pageviews":N}}]}.