Skip to main content
The Hikoo MCP ships 86 tools across the areas below. You never call them directly. Describe what you want in natural language and your client picks the right one. Four discovery tools take no website_id. Every other tool is a data tool and requires a website_id, which your client obtains from discovery first. Each tool is labelled so clients know how to treat it:

​
Discovery

No website_id needed. Start here to find the site you want to work on.
​
read-only
The signed-in user (id, email, name).
​
read-only
Flat list of the workspaces you belong to, with your role in each.
​
read-only
One-shot tree of your workspaces and the websites inside each, with has_active_subscription and plan tier. The preferred way to pick a site.
​
read-only
Paginated websites with subscription status.Args: workspace_id (optional), page, page_size

​
Website and subscription

​
read-only
Website metadata: url, name, aliases, topics, competitors, language, and subscription status.Args: website_id
​
read-only
Full plan detail: tier, status, trial and expiry, tracked AI platforms, feature availability, and every quota. Owner or admin only.Args: website_id

​
Audits

​
read-only
Audit quota used, limit, and remaining for the current period.Args: website_id
​
read-only
Every audit ever run for the website, most recent first, with scores, status, and page counts.Args: website_id
​
read-only
One audit: overall score, timing, and the list of audited pages.Args: website_id, audit_id
​
read-only
Page-level result with every criterion and its pass/fail status, plus the recommendations on each failing criterion. The most detailed audit view.Args: website_id, audit_id, page_id
​
write
Queue a new full-site audit. Runs asynchronously and counts against your quota.Args: website_id
​
write
Queue an audit of a single URL. The URL must be on the website’s domain.Args: website_id, url
​
write
Queue an audit of a specific list of URLs, capped by your plan.Args: website_id, urls
​
write
Re-run an audit, reusing a prior audit’s page set and criteria.Args: website_id, audit_id

​
Citations

​
read-only
Paginated AI citations: the content the assistant produced, its sources, and which competitors were mentioned.Args: website_id, page, page_size, time_range, website_cited
​
read-only
One citation in full: the assistant’s answer, sources, brand mentions with sentiment, the triggering prompt, and competitor ranks.Args: website_id, citation_id
​
read-only
Top AI platforms by citation count.Args: website_id, time_range
​
read-only
Visibility over time per platform: in each period, the share of that platform’s answers that name your website.Args: website_id, time_range
​
read-only
Top source domains or URLs that appear in AI citations.Args: website_id, time_range, group_by (domain or url), limit
​
read-only
Uncapped, paginated list of every source URL by frequency.Args: website_id, page, page_size, time_range, source_class (all, mentioned, background)
​
read-only
Counts per match type (brand citation, site mention, background source) with a delta and a sparkline. Capped at 1 year.Args: website_id, time_range, tz
​
read-only
Where one URL shows up: AI answers that cited it, and AI crawlers that fetched it. Accepts a full URL, a bare domain, or a path.Args: website_id, url, time_range, citations_limit, pages_limit

​
Sentiment

Available on some plans. Both tools return 403 if sentiment analysis is not on your plan, and cover up to 1 year.
​
read-only
Positive, negative, and neutral counts per brand (your site, competitors, unresolved).Args: website_id, time_range
​
read-only
Sentiment counts bucketed over time.Args: website_id, time_range, bucket (day or week)

​
AI-crawler traffic

Traffic that AI agents (GPTBot, ClaudeBot, PerplexityBot and others) send to your own website. Available on some plans.
​
read-only
Total visits, unique agents, unique pages, a row per vendor, and a visit trend.Args: website_id, time_range, vendors
​
read-only
The URLs AI crawlers fetched on your website, most visited first, with the change against the previous period and the agents behind each visit.Args: website_id, page, page_size, time_range, vendors, search

​
Competitors

​
read-only
Competitor ranking (share of voice) against your website.Args: website_id, time_range
​
read-only
Citation counts per competitor.Args: website_id, time_range
​
read-only
Share-of-voice chart data for your site plus competitors.Args: website_id, time_range
​
read-only
Time series of your share of voice versus all competitors.Args: website_id, time_range
​
read-only
The maximum number of tracked competitors on your plan.Args: website_id
​
read-only
Competitors auto-discovered from your citations (available on some plans).Args: website_id
​
read-only
The AI answers behind one competitor suggestion: prompt, platform, and the rank the brand held in each answer.Args: website_id, suggestion_id, page, page_size
​
write
Add a tracked competitor. Enforces your competitor limit.Args: website_id, name, url, aliases
​
write
Update a competitor’s name, URL, or aliases.Args: website_id, competitor_id, name, url, aliases
​
write
Hide a suggested competitor.Args: website_id, suggestion_id
​
write
Promote a suggestion to a tracked competitor. Enforces your limit, and is available on some plans.Args: website_id, suggestion_id, url, logo_url, aliases
​
destructive
Remove a tracked competitor.Args: website_id, competitor_id

​
Content gap

Available on some plans. A limit of 0 means content gap is not on your plan.
​
read-only
Monthly content-gap quota used, limit, and reset date.Args: website_id
​
read-only
Counts of gap suggestions by status and priority.Args: website_id
​
read-only
Paginated gap suggestions, sorted by similarity (the lowest is the biggest gap).Args: website_id, status, min_score, max_score, limit, offset
​
read-only
Full gap detail: brief, outline, reasoning, the competitor topic, and your closest existing page.Args: website_id, suggestion_id

​
Health

​
read-only
Global website health (AI crawlers allowed, llms.txt present, sitemap reachable) plus improvement suggestions.Args: website_id, include_dismissed
​
read-only
Monthly health-refresh quota used, limit, and reset date.Args: website_id
​
read-only
Monthly suggestion-regeneration quota.Args: website_id
​
read-only
Paginated indexed pages affected by a health suggestion.Args: website_id, suggestion_id, page, per_page
​
write
Force a re-check of robots.txt, llms.txt, and sitemap. Quota-limited.Args: website_id
​
write
Hide a health suggestion.Args: website_id, suggestion_id
​
write
Un-hide a dismissed health suggestion.Args: website_id, suggestion_id
​
write
Regenerate suggestions from your indexed pages. Quota-limited.Args: website_id

​
Indexation and pages

​
read-only
Aggregated page stats: total, by category, pass rate, errors and warnings, and last crawl.Args: website_id
​
read-only
The latest indexation job status and progress counters.Args: website_id
​
read-only
Paginated indexed pages, filterable.Args: website_id, category, health_passed, has_errors, has_warnings, language, search, limit, offset
​
read-only
One indexed page: URL, title, language, category, last crawl, health, and errors.Args: website_id, page_id
​
read-only
The most common health-check errors grouped by type with counts.Args: website_id, limit
​
write
Trigger a re-crawl of a single URL on the domain. Poll status afterward.Args: website_id, url

​
Prompts

​
read-only
Prompts used versus your plan limit. Call this before bulk-creating prompts.Args: website_id
​
read-only
All prompts, grouped by topic, each with its visibility score.Args: website_id, topic_id
​
read-only
Paginated citations tied to a prompt.Args: website_id, prompt_id, page, page_size
​
read-only
Drill-down for a prompt: visibility with a 7-day delta, best rank and platform, coverage, a 30-day sparkline, a per-platform grid, and the latest answers.Args: website_id, prompt_id, answers_limit
​
read-only
Aggregated visibility stats across all of a prompt’s citations.Args: website_id, prompt_id
​
read-only
Every AI answer of one prompt, newest first, one page at a time. Pass next_cursor back as cursor until it is null.Args: website_id, prompt_id, limit, cursor
​
write
Create a prompt. Enforces your prompt quota.Args: website_id, content, topic_id, localizations
​
write
Update one prompt. Only the fields you provide change.Args: website_id, prompt_id, content, topic_id, localizations, intent, journey_stage
​
write
Apply the same metadata edit to many prompts at once (up to 1500).Args: website_id, prompt_ids, topic_id, intent, journey_stage
​
write
Stop tracking prompts and free their quota slots. Their history is kept and hk_restore_prompt brings them back. Up to 1500 ids.Args: website_id, prompt_ids
​
write
Put an archived prompt back into tracking. It takes a free quota slot, or replace_with names an active prompt to archive in exchange. A deleted prompt cannot be restored.Args: website_id, prompt_id, replace_with
​
destructive
Delete a prompt.Args: website_id, prompt_id

​
Topics

​
read-only
Every topic tracked for the website.Args: website_id
​
write
Create a topic for organizing prompts.Args: website_id, name
​
write
Rename a topic.Args: website_id, topic_id, name
​
destructive
Delete a topic.Args: website_id, topic_id

​
Search queries

​
read-only
The searches AI assistants ran while answering your prompts, clustered by topic or by prompt, with counts, platforms, and the most frequent queries of each cluster.Args: website_id, group_by, sort, page, page_size, queries_limit, platforms, topic_ids, q, time_range, date_from, date_to
​
read-only
One page of the queries of a single cluster, most frequent first.Args: website_id, group_by, group_id, page, page_size, platforms, topic_ids, q, time_range, date_from, date_to
​
read-only
The unique search-query variants AI assistants executed for your site.Args: website_id, page, page_size, platform
​
read-only
Query variants triggered by one prompt.Args: website_id, prompt_id, page, page_size
​
read-only
Query variants attached to one citation.Args: website_id, citation_id, page, page_size

​
Source intelligence

​
read-only
Aggregated source counts by source_type and by AI platform.Args: website_id
​
read-only
The domains AI assistants cite when they answer about your space, ordered by citation count.Args: website_id, source_type, platform, search, limit, offset
The list covers the most-cited sources your plan includes.
​
read-only
The cited pages one by one, and which brands are on each. relation tells them apart: owned (only your brand), contested (you and a competitor), lost_ground (competitors without you), open (neither). An absence only counts when presence_known is true.Args: website_id, relation, present, topic_id, search, momentum, actionable_only, active_only, limit, offset

​
Agency reports

For agency workspaces. These tools take a workspace_id, not a website_id. An agency adds a list of sites, Hikoo grades each one, and every launched report gets its own shareable link.
​
read-only
The reports of an agency workspace, with their links once built and the date each link expires.Args: workspace_id, status, search, page, page_size
​
write
Grade a list of sites and save nothing. Each row comes back accepted or refused, with the reason.Args: workspace_id, sites
​
write
Create the rows that grade OK. Adding does not launch them.Args: workspace_id, sites
​
write
Start every report still waiting. This takes the whole pending batch and spends the workspace’s report quota.Args: workspace_id
​
write
Build the named reports again. Their links keep working throughout.Args: workspace_id, report_ids
​
destructive
Turn off the shared links of the named reports. Anybody opening one afterwards sees nothing.Args: workspace_id, report_ids

​
Argument conventions

  • time_range accepts: all_time, 1y, 1m, 1w, 1d. Sentiment and breakdown tools cap the range at 1 year.
  • Pagination comes in a few styles. Most tools use page and page_size (1-based), content gaps and pages and suggested sources use limit and offset, and health suggestion pages use page and per_page.
  • Enums you may pass:
    • Prompt intent: informational, comparative, transactional, navigational.
    • Prompt journey_stage: discovery, consideration, decision, retention.
    • Search-query platform: chatgpt, perplexity, gemini, claude, copilot.
    • Source source_type: review_platform, media, blog, directory, forum, wiki, social.
    • Top-sources group_by: domain, url. Sources source_class: all, mentioned, background.
    • Content-gap status: pending, in_progress, completed, dismissed.
  • Write and destructive tools change data in your workspace. Claude Desktop and Claude Code ask for confirmation before running them by default.