MCP App Store
by KeenEthics
Hikoo icon

Hikoo MCP Server for ChatGPT

By Hikoo

Overview

Hikoo measures how a website shows up in the answers of AI assistants. This plugin connects to the Hikoo account the user already has, so they can ask about their own data in plain language. What it can read: the workspaces and websites in the account; AI answers that cited the website and the source pages those answers relied on; competitors and their share of AI answers over time; sentiment; GEO and SEO audits of the website's pages; AI-crawler traffic and crawler access health; page indexation; tracked prompts and topics; and stored content-gap recommendations. What it can change, always inside the user's own account and only with their confirmation: tracked prompts and topics, competitors and competitor suggestions, audits, health refreshes and suggestions, URL indexation requests, and shareable agency reports for workspaces that have them. Sign-in uses OAuth with the user's Hikoo account. On the consent screen the user chooses read-only or read and write access, and can disconnect at any time from the API keys page in Hikoo.

How to connect

  1. ChatGPT: Open the Hikoo listing in the ChatGPT app directory and choose Connect. ChatGPT listing Hikoo exposes 86 tools here.

Tools

hk_add_agency_reports

ChatGPT
Create the rows that grade OK. This does not launch them. The batch is graded again here rather than trusting a previous preview, so what is created is what the server accepted. Rows that fail are reported and simply not created.

hk_add_competitor

ChatGPT
Add a competitor directly (without going through a suggestion). Plan quota (`competitors_limit) is enforced server-side; hk_get_competitors_quota` holds the limit it counts against.

hk_archive_prompts

ChatGPT
Archive active prompts: they stop being tracked and free their quota slot. The history is kept and the archive never expires; unlike a delete, `hk_restore_prompt puts the prompt back. Prompts already archived, deleted or still drafts are skipped. Takes up to 1500 ids. Returns {archived: <count>}`.

hk_audit_pages

ChatGPT
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.

hk_audit_url

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

hk_batch_update_prompts

ChatGPT
Apply the same metadata edit to many prompts in one call. Sets `topic_id, intent and/or journey_stage on every prompt in prompt_ids (max 1500). Only the fields you pass are written - omit a field to leave it untouched on every prompt. Returns {updated: <count>}. Use hk_update_prompt to also edit a single prompt's content or localizations`.

hk_create_prompt

ChatGPT
Create a new prompt for the target website. Each create counts against the limit `hk_get_prompts_quota` reports; every create beyond it fails with "Prompt limit reached".

hk_create_topic

ChatGPT
Create a new topic for organizing prompts.

hk_delete_prompt

ChatGPT
Delete a prompt from the target website.

hk_delete_topic

ChatGPT
Delete a topic from the website.

hk_dismiss_competitor_suggestion

ChatGPT
Hide a suggested competitor so it stops appearing in the list.

hk_dismiss_health_suggestion

ChatGPT
Hide a health suggestion so it stops showing in the overview.

hk_get_agent_analytics

ChatGPT
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).

hk_get_audit

ChatGPT
Return a specific audit with its audited pages.

hk_get_audit_page

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

hk_get_audits_quota

ChatGPT
Audit quota (used / limit / remaining) for the current billing period. This is the cap `hk_start_audit` spends from; at zero it refuses.

hk_get_citation

ChatGPT
Single citation by id: full LLM response content, the sources it cited, every brand mentioned with sentiment highlights, the prompt that triggered it, and competitor ranks. `brand_mentions` is stripped when the plan disables sentiment.

hk_get_citation_search_queries

ChatGPT
All search-query variants attached to a single citation. Use to debug which AI sub-question produced a citation.

hk_get_citations_breakdown

ChatGPT
Per-match_type counts for the requested period: `brand_mention (the brand named, the visibility), cited_link (a link to the site shown) and background_link (the site read, not shown), each with its delta vs the previous period and a daily sparkline. The former values brand_citation / site_mention / background_source are still accepted as filters. time_range` is capped at 1 year.

hk_get_competitive_share_over_time

ChatGPT
Time series of the tracked website's citation share of voice relative to all competitors.

hk_get_competitor_citations

ChatGPT
Citation counts per competitor for the requested period.

hk_get_competitor_suggestion_citations

ChatGPT
The AI answers behind one competitor suggestion, most recent first. Every chat where the citation analyzer saw this entity, with the prompt that triggered it, the platform, and the rank it held in that answer (`rank / rank_total): the evidence behind the suggestion's citation_count`.

hk_get_competitors_chart

ChatGPT
Share of voice chart data for the website and its competitors.

hk_get_competitors_quota

ChatGPT
Plan-based competitor quota: `limit` is the maximum number of tracked competitors allowed. Adding or promoting past it refuses.

hk_get_content_gap

ChatGPT
Full detail of a content-gap suggestion: brief, outline, reasoning, the competitor topic that produced it, and the closest existing page on the website. Plan-gated.

hk_get_content_gap_quota

ChatGPT
Monthly content-gap analysis quota: used, limit, resets_at. A limit of 0 means the plan does not include content gap.

hk_get_content_gap_summary

ChatGPT
Counts of content-gap suggestions by status and priority. Plan-gated. 403 if content gap is not on the plan.

hk_get_health

ChatGPT
Global health (AI crawlers allowed, llms.txt present, sitemap present) + improvement suggestions for the target website.

hk_get_health_refresh_quota

ChatGPT
Used / limit / resets_at for the website's monthly health refreshes.

hk_get_indexation_status

ChatGPT
Latest indexation job status (running, completed, failed) plus progress counters.

hk_get_indexation_summary

ChatGPT
Aggregated stats on indexed pages: total, by category, health pass rate, pages with errors or warnings, last crawl timestamp.

hk_get_page

ChatGPT
Detail of one indexed page: URL, title, language, category, last crawled at, health status, errors, and `search_metrics (clicks and impressions in Google and Bing over the same time filter as hk_list_pages`; null per provider when the site has not connected it).

hk_get_prompt_citations

ChatGPT
Paginated citations tied to a specific prompt (actual AI responses).

hk_get_prompt_detail

ChatGPT
Drill-down aggregate for one prompt: visibility + 7d delta, average position + 7d delta, best rank with platform, coverage X/N, 30-day sparkline, per-platform coverage grid, and the latest N answers.

hk_get_prompt_search_queries

ChatGPT
Unique search-query variants triggered by one prompt.

hk_get_prompt_stats

ChatGPT
Visibility of a prompt over every answer: `answer_count, brand_mentions (answers naming the website) and visibility`.

hk_get_prompts_quota

ChatGPT
How many prompts are active vs the subscription limit. This is the cap creating or restoring a prompt spends from. Archived prompts do not count. Returns `{used, limit, remaining}. A batch larger than remaining` stops at the limit.

hk_get_sentiment_summary

ChatGPT
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.

hk_get_sentiment_trend

ChatGPT
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.

hk_get_source_intelligence_stats

ChatGPT
Aggregated source counts: by source_type and by AI platform. The shape of what `hk_list_suggested_sources` returns in full: which kinds of sources exist and which platforms drive citations.

hk_get_subscription_details

ChatGPT
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). This is what a 403 from a data tool refers back to: the features and quotas this website's plan covers. Restricted to workspace OWNER and ADMIN. Members get 403 because billing info is sensitive.

hk_get_suggestion_pages

ChatGPT
Paginated list of indexed pages affected by a specific health suggestion.

hk_get_suggestion_regen_quota

ChatGPT
Used / limit / resets_at for monthly suggestion regenerations.

hk_get_top_platforms

ChatGPT
Top AI platforms for the target website: answers naming it (`citation_count), answers collected (answer_count) and their ratio (visibility`, in percent).

hk_get_top_sources

ChatGPT
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. scope`: "own" keeps only the tracked website's own pages (aliases included), "external" everything else.

hk_get_visibility_by_platform

ChatGPT
Visibility over time per platform: in each bucket, the share of that platform's answers that name the website (formerly `hk_get_platforms_share_of_voice`).

hk_get_website

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

hk_index_url

ChatGPT
Trigger a re-crawl of a single URL, fetched live from the website. The URL must belong to the website's domain. Returns a job handle; its completion shows in `hk_get_indexation_status`.

hk_launch_agency_reports

ChatGPT
Start every report still waiting, and spend the quota for them. There is no way to launch a subset: this is the screen's button and it takes the whole pending batch. The quota it spends is real money and does not come back.

hk_list_agency_reports

ChatGPT
The reports in an agency workspace, with their links when they exist. `report_slug is the deliverable and is null until the report has been launched and built. report_expires_at` is when the link stops working; a revoked report loses its slug rather than keeping a dead one.

hk_list_agent_pages

ChatGPT
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. hk_lookup_url` covers a single URL across both AI-crawler traffic and citations in one call.

hk_list_all_sources

ChatGPT
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 to the unfiltered one. scope: "own" keeps only the tracked website's own pages (aliases included), "external" everything else. search: case-insensitive substring match on the full URL, to find one specific page or every URL from one domain. Percentages stay relative to the whole source volume, so a filtered row's share is still comparable. hk_lookup_url` covers a single URL across both citations and AI-crawler traffic in one call.

hk_list_audits

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

hk_list_citations

ChatGPT
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.

hk_list_competitor_suggestions

ChatGPT
List competitor candidates surfaced by the citation analyzer. Plan-gated. Returns 403 if the website's plan disables competitor suggestions. Each item has `id, display_name, citation_count, and timestamps; use those ids with hk_dismiss_competitor_suggestion, hk_promote_competitor_suggestion or hk_get_competitor_suggestion_citations`. Only entities that are both recurrent (more than 10 citations) and current (seen in the last 14 days) surface here, so an empty list means no live candidate, not no data.

hk_list_competitors

ChatGPT
Competitor ranking (share of voice) for the target website.

hk_list_content_gaps

ChatGPT
Paginated content-gap suggestions, sorted by similarity score (lowest first means biggest gaps). Plan-gated. 403 if content gap is not on the plan.

hk_list_page_errors

ChatGPT
Most common health-check errors across the website's indexed pages, grouped by error type with counts.

hk_list_pages

ChatGPT
Paginated list of indexed pages, filterable by category, health status, error/warning flags, language, and URL/title search. `status filters on the page's derived state: blocked (bot protection), not_crawled (content never read yet), crawled (read, but its category was only guessed from the URL, no LLM or person decided it yet), errors, warnings or analysed. Every row carries its status. Every row also carries search_metrics: the page's clicks and impressions in Google (google, from Google Search Console) and in Bing (bing, from Bing Webmaster Tools), totals over the time filter: time_range (1w, 1m, 1y, all_time), counted back from the latest day with data, or date_from / date_to (YYYY-MM-DD, win over time_range); all time (every day kept since the connection, 16 months back at least) by default. A provider is null when the site has not connected it or has no data in the filter; zeros mean it is connected and the page had no impression. search_sources lists the connected providers with the exact days summed (period_start to period_end; Google lags 2 to 3 days, Bing is weekly so its totals cover whole weeks). sort_by (google_impressions, google_clicks, bing_impressions, bing_clicks) with sort_direction (desc default, asc`) orders the pages by one of them.

hk_list_prompt_answers

ChatGPT
Every AI answer of one prompt, newest first, one page at a time: `items (platform, content, rank, date, brand mentions) and next_cursor. Pass next_cursor back as cursor until it is null. Use hk_get_prompt_detail` for the aggregate view.

hk_list_prompts

ChatGPT
List prompts tracked for the target website, grouped by topic, each with its `visibility (% of its answers that name the website). Optional filters: brand_scopes (branded / non_branded) and intents` (informational / comparative / transactional / navigational) narrow the list to prompts matching any of the given values.

hk_list_search_queries

ChatGPT
Unique AI search-query variants executed for the website. These are the sub-questions a model spun off from prompts before producing citations. Useful for understanding which intents drive visibility.

hk_list_search_queries_in_group

ChatGPT
One page of the queries of a single cluster from `hk_list_search_query_groups, most generated first. group_id is the topic or prompt id (per group_by`); omit it for the unclustered bucket. Pass the same filters as the cluster list to read the same set.

hk_list_search_query_groups

ChatGPT
Query fanouts (the searches AI assistants ran while answering the tracked prompts) clustered by `group_by ("topic" or "prompt"), paginated by cluster. Each cluster carries query_count (distinct queries), total_count (generations), its platforms and up to queries_limit of its most generated queries; page the rest with hk_list_search_queries_in_group. sort: "frequency" (most generated), "queries" (most distinct queries) or "recent". date_from / date_to (YYYY-MM-DD) override time_range`.

hk_list_source_pages

ChatGPT
Cited pages one by one, and who is already on each of them. `hk_list_suggested_sources lists DOMAINS and says nothing about presence. This is the per-URL surface the dashboard reads: the page, its citation signal, and the brands found on it. relation is the whole point: - owned: only the tracked brand is on the page - contested: the brand and at least one competitor - lost_ground: competitors are there, the brand is not - open: neither found. Only meaningful when presence_known is true; it is also the default for a page nobody has read. Read presence_known before drawing any conclusion from an absence. False means nobody has opened the page: the brand list is empty because it was never fetched, not because the page has no brands on it. relation: open on such a row is a default, not a finding, and reporting it as "you are not on this page" states something nobody checked. Source Intelligence works through these on its own schedule, so it turns true on its own. presence_status carries the dedicated scrape when one has run, including blocked for a page that could not be read at all. momentum is the other half of the picture, and it is on every row whether or not you filter on it: a page cited forty times reads the same in a list whether the engines started quoting it last month or stopped. new and surging are where a week's work goes; dormant is a page that has not been cited in thirty days, which is worth knowing before writing to its editor about it. The result is the plan's visibility window, ordered by opportunity. plan_max and total_in_store` come back with it: when they differ, this is a slice, and calling it "all your sources" is wrong.

hk_list_suggested_sources

ChatGPT
Suggested sources Hikoo discovered via AI citations for the target website. Shows where the assistants get their answers for this space: review platforms and directories, media and blogs, forums and social.

hk_list_topics

ChatGPT
List all topics tracked for the target website.

hk_list_websites

ChatGPT
List websites the user can access. Each item carries `has_active_subscription. A site with false` returns 403 from every data endpoint, so its data is unavailable while that is the case.

hk_list_workspaces

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

hk_list_workspaces_with_websites

ChatGPT
One-shot discovery tree: every workspace the user belongs to, with its websites nested inside (id, name, url, `has_active_subscription, plan_tier). The whole picker in one call: hk_list_workspaces and hk_list_websites each return one half of the same tree. Data tools take their website_id from it. A site with has_active_subscription=false` returns 403 on data endpoints, so its data is unavailable while that is the case.

hk_lookup_url

ChatGPT
Where does this URL show up? One call, both surfaces. One call covers both surfaces, where searching cited sources and crawler traffic separately takes two. `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 seen, and the most recent matching answers. agent_traffic: pages AI crawlers actually fetched on the website, with visit counts and which agents did the fetching. When agent_traffic.enabled is false the plan does not include agent analytics, so zero hits means "not measured", not "never visited". url accepts a full URL, a bare domain, or a path. Scheme, www.`, query string and fragment are stripped before matching, and the match is a case-insensitive substring — so a domain finds every page under it.

hk_preview_agency_reports

ChatGPT
Grade a batch and write nothing. Each row comes back with a verdict and, when it is refused, the reason. Fixing the list here is free; adding a bad batch creates half of it and leaves the agency to clean up.

hk_promote_competitor_suggestion

ChatGPT
Promote a suggested competitor to a tracked Competitor row. `url is required (Competitor model). The plan's competitor quota is enforced server-side; hk_get_competitors_quota` holds the limit it counts against.

hk_refresh_health

ChatGPT
Force a re-check of robots.txt, llms.txt, and sitemap, fetched live from the website itself. Quota-limited per the website's plan; `hk_get_health_refresh_quota` reports what is left.

hk_regenerate_health_suggestions

ChatGPT
Regenerate health suggestions from currently indexed pages. Quota-limited.

hk_relaunch_agency_reports

ChatGPT
Run the named reports again. Their links keep working throughout.

hk_remove_competitor

ChatGPT
Remove a tracked competitor from the website.

hk_restore_health_suggestion

ChatGPT
Bring a previously dismissed health suggestion back into the overview.

hk_restore_prompt

ChatGPT
Put an archived prompt back into tracking. A restore takes a free quota slot. `replace_with` names an active prompt archived in exchange: required when no slot is free, allowed when one is. A deleted prompt cannot be restored. Returns the restored prompt.

hk_revoke_agency_reports

ChatGPT
Kill the shared links. A client opening one afterwards sees nothing. These links have usually been sent to somebody outside Hikoo, so the effect is visible to people the agency does not control.

hk_start_audit

ChatGPT
Queue a new full-site audit for the target website. Async: its status shows in `hk_list_audits and hk_get_audit`. Fails if the website's audit quota for the current period is exhausted.

hk_sync_audit

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

hk_update_competitor

ChatGPT
Update a competitor's name, URL, or aliases.

hk_update_prompt

ChatGPT
Update an existing prompt's content or metadata. Only provided fields are changed. Editable fields: `content, localizations (the prompt's target locales/markets), topic_id (the topic the prompt belongs to), intent (informational / comparative / transactional / navigational) and journey_stage (discovery / consideration / decision / retention). To edit many prompts at once, use hk_batch_update_prompts`.

hk_update_topic

ChatGPT
Rename a topic.

hk_whoami

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

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/hikoo"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/hikoo)