hk_mcp

Showing 25 of 89 from the live probe.

• Who Am I

  Return the user the current API key is bound to (id, email, full_name).

• List Workspaces

  List every workspace the user belongs to (id, name, role).

• Workspaces with Websites

  One-shot discovery tree: every workspace the user belongs to, with its websites nested inside (id, name, url, ``has_active_subscription``, ``plan_tier``). Prefer this over ``hk_list_workspaces`` + ``hk_list_websites`` when the user has not yet picked a target. The agent can show the whole tree, the user picks, and you call data tools with the chosen ``website_id``. Sites with ``has_active_subscription=false`` return 403 on data endpoints, so ask the user to upgrade or pick another.

• List Websites

  List websites the user can access. Always call this first when the user has not yet picked a website. Each item carries ``has_active_subscription``. Sites with ``false`` will return 403 from any data endpoint, so you should ask the user to subscribe (or pick another site) before drilling in.

• Get Website

  Return metadata and subscription info for a website the user can access.

• Subscription Details

  Detailed plan info for the website: plan tier, product name, status, trial/expiry dates, AI platforms covered, feature flags (sentiment, competitor suggestions, source intelligence, exports, AI prompt generation), and every quota (audits, prompts, competitors, indexation pages, content gap runs, health refreshes, suggestion regenerations). Use this to tell the user which features require an upgrade before hitting a 403 on a data tool. Restricted to workspace OWNER and ADMIN. Members get 403 be

• Get AI Agent Traffic

  AI-crawler traffic dashboard: total visits, unique agents, unique pages, per-vendor rows and a visit trend. This is traffic AI agents (GPTBot, ClaudeBot, PerplexityBot, ...) sent to the website itself — not citations. Plan-gated: 403 when agent analytics is not in the website's plan. ``vendors``: optional comma-separated vendor codes to narrow every metric (the ``vendors`` list in the response always stays complete).

• List URLs Visited By AI Agents

  Paginated URLs AI crawlers fetched on the website, visits desc. Each row carries the path, the visit count, the delta vs the previous window, and the per-agent breakdown. ``search``: case-insensitive substring match on the visited URL. A pasted full URL is normalized first (scheme, ``www.``, query string and fragment dropped), so ``https://www.example.com/blog?utm=x`` and ``/blog`` both match. To check a single URL across BOTH AI-crawler traffic and citations in one call, use ``hk_lookup_url``

• Look Up A URL Everywhere

  Where does this URL show up? One call, both surfaces. Use this whenever the user hands you a URL and asks whether it appears anywhere — it saves searching sources and agent traffic separately. ``sources``: AI answers that cited a matching URL while answering the website's prompts. Carries how many answers, on which platforms, from which prompts, whether the URL was shown to the user (``mentioned_count``) or only consulted in the background (``background_count``), the first/last time it was see

• Audit Quota

  Audit quota (used / limit / remaining) for the current billing period. Call BEFORE ``hk_start_audit`` to avoid hitting the cap.

• List Audits

  List all audits for the target website (most recent first).

• Get Audit

  Return a specific audit with its audited pages.

• Start Audit

  Queue a new full-site audit for the target website. Async. Poll ``hk_list_audits`` / ``hk_get_audit`` for status. Fails if the website's audit quota for the current period is exhausted.

• Get Audit Page Detail

  Detailed audit result for a single page. Every criterion with its validation status (pass/fail) and the recommendations produced for it.

• Audit Single URL

  Queue a one-URL GEO audit. ``url`` must belong to the website's domain. Counts against the audit quota.

• Audit Selected Pages

  Queue an audit on a specific list of URLs. All URLs must belong to the website's domain. The number of URLs is capped by the plan's per-audit page allowance. Counts against the audit quota.

• Sync Audit

  Queue a new audit reusing the page set and criteria of a previously completed audit. Cheap re-check after content changes.

• List Citations

  Paginated list of AI citations for the target website. Each item includes the full content returned by the LLM, the sources it cited, the competitors mentioned, and whether the website itself was cited.

• Top AI Platforms

  Top AI platforms by citation count for the target website.

• Visibility Trend per Platform

  Visibility trend data per platform (share of voice over time).

• Top Source Domains

  Top source domains (or URLs) appearing in AI citations for the target website. ``group_by="url"`` returns full URLs; ``domain`` carries the grouping key either way, and ``url`` is set in URL mode. ``source_class``: "mentioned" keeps the URLs surfaced to the reader (inline citation, pill or attached link), "background" the ones only consulted during retrieval. The two overlap when a page is shown in one answer and merely read in another, so their counts do not add up to the unfiltered total. `

• Sentiment Summary by Brand

  Aggregated sentiment (positive/negative/neutral counts) per brand mentioned in AI citations: tracked website, tracked competitors, and unresolved entities. Plan-gated: returns 403 when sentiment analysis is not enabled on the website's subscription. ``time_range`` is capped at 1 year.

• Sentiment Trend Over Time

  Sentiment counts bucketed by day or week. Each point has positive_count, negative_count, neutral_count, mention_count, and citation_count for the bucket. Plan-gated. 403 when sentiment analysis is disabled. ``time_range`` is capped at 1 year.

• Citations Breakdown by Match Type

  Per-match_type counts (brand_citation, site_mention, background_source) for the requested period, with delta vs previous period and a daily sparkline. Powers trend reporting. ``time_range`` is capped at 1 year.

• List All Source URLs

  Paginated full URLs cited in AI responses, sorted by frequency. Unlike hk_get_top_sources this is uncapped and returns the full URL, not the domain. ``source_class``: "mentioned" keeps the URLs surfaced to the reader (inline citation, pill or attached link), "background" the ones only consulted during retrieval; omit for all. The split is per URL and per answer, so the same page counts as mentioned in one response and background in another: the two filters overlap and their totals do not add up