VisibilityKit MCP server

• Addresshttps://visibilitykit.app/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on visibilitykit.app when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

• Stateanswerschecked 2026-10-27
• Tools37
• Server calls itselfvisibilitykit
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 206 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer566 ms
• Space in an agent's context≈ 6,799 tokensthe definitions of all its tools (37), which an agent carries on every turn
• Tool definitionsA · 98 of 100
• Typed results2 of 37 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 5 of 37

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_brands

  List the brands (websites) the user tracks in VisibilityKit. Use this first when the user has not said which brand they mean or another tool asks for a brand.

• get_visibility_overview

  Show a brand's AI search visibility: how often ChatGPT, Perplexity, Gemini and other AI engines mention or cite the brand, the trend versus the previous period, per-engine scores, strongest and weakest topics, and share of voice against…

• get_topics

  List the topics (groups of AI prompts) VisibilityKit tracks for a brand, with each topic's visibility score, change versus the previous period and per-engine breakdown. Use to find which subjects the brand wins or loses in AI answers.

• get_competitors

  Compare a brand with its competitors in AI answers: share of voice for each, whether each competitor is ahead, behind or even, their strongest AI engine, and newly discovered competitors VisibilityKit suggests tracking.

• get_citation_sources

  List the websites AI engines cite when answering the brand's tracked prompts, with each domain's citation share and whether it cites the brand, competitors, or both. Filter "gap" returns sources that cite competitors but not the brand…

• get_citation_gaps

  Rank the citation gaps for a brand: high-impact websites that AI engines rely on for its topics but that do not mention the brand yet, with the reason each one matters. Use when the user asks where to get mentioned or what to do next.

• get_recommendations

  Get evidence-backed fixes VisibilityKit recommends to raise a brand's AI citations, ordered by expected lift, with the effort each takes. Use when the user asks how to improve their AI visibility.

• get_prompt_performance

  Show, prompt by prompt, whether each AI engine mentions, cites or recommends the brand. Filter "not_mentioned" lists the tracked prompts where no AI engine mentions the brand — the questions it is invisible for. Each row has the latest…

• get_ai_answer

  Read one AI answer VisibilityKit collected: the prompt, the engine and model, the answer text (first 4,000 characters), its cited sources (flagging the brand's own site), which brands it mentioned and in what position, claims made about…

• get_visibility_changes

  List what changed in the brand's AI visibility recently: significant score rises and drops per topic and engine, competitors overtaking the brand, and sources that started citing it. Use for "what changed?", "why did my visibility drop?"…

• explain_topic_score

  Explain why the brand scores what it does on one topic, from the collected answers: outcome breakdown (recommended, cited, mentioned, absent), the sources AI engines cite and whether the brand's site is among them, and competitors…

• get_brand_perception

  Show how AI engines talk about the brand: the share of answers with positive, neutral and negative sentiment per engine, the weekly trend over the last 8 weeks with data, and recent AI model releases that may explain shifts. Engines are…

• get_competitor_head_to_head

  Compare the brand with one tracked competitor in AI answers: how often AI answers recommend or cite the brand versus how often they recommend the competitor (overall and per engine), the topics each one wins, sources that cite only the…

• compare_engines

  Compare how visible the brand is on each AI engine (ChatGPT, Perplexity, Gemini, Google AI Overviews, …) and find the topics where engines disagree most — e.g. strong on Perplexity but invisible on ChatGPT. Use for "which AI engine is…

• get_site_health

  Technical and AEO health of the brand's website from VisibilityKit page audits: average technical, content and AI-readiness scores, open issues by severity and type (missing schema, thin content, slow pages, broken links…), the weakest…

• get_page_analysis

  Analyze one page of the brand's site from its latest VisibilityKit audit: technical, content and AI-readiness scores, HTTP status, sitemap presence, and every open issue with the fix. Use for "how AI-ready is this page?" or "what should I…

• get_ai_understanding

  Entity analysis: which facts about the brand (pricing, plans, features, integrations, availability, company facts) each AI engine knows, gets partly right, doesn't know, or contradicts — plus the associations and framing AI attaches to…

• get_content_gaps

  Find content gaps: facts about the brand that AI engines don't know yet (ranked by impact, with the format to publish them in), facts an engine states wrongly, and themes AI associates with competitors instead of the brand. Use for "what…

• get_action_queue

  The brand's open to-do list in VisibilityKit, highest priority first: opportunities, evidence-backed recommendations, content to create or optimize, and audit actions, merged into one queue. Use for "what should I do next?" or a weekly…

• get_content_job

  Check a VisibilityKit content-generation job (from generate_content or the app): its state and, once written, the title and article text (first 6,000 characters). Content marked needsReview waits for a human review in VisibilityKit before…

• list_reports

  List the brand's generated VisibilityKit PDF reports, newest first, with a download link for each finished one (links expire after about an hour — call again for a fresh one). Pass report_id for one report.

• export_data

  Export VisibilityKit data as CSV for a spreadsheet: "prompts" (outcome per prompt and engine), "topics" (visibility per topic and engine), "competitors" (share of voice) or "citation_sources" (cited domains). Returns the CSV text; offer…

• export_answer_card

  Render one collected AI answer as a shareable PNG card (branded with the workspace logo and colors when set), for a slide or a client update. Get run_id from get_prompt_performance.

• get_monitoring_schedule

  Show when VisibilityKit monitors the brand automatically: the next AI visibility run, and the schedule (daily, weekly, monthly or custom) and next run of citation checks, page audits and other recurring jobs, flagging any that are failing.

• get_alert_settings

  Show the user's own VisibilityKit alert settings for a brand's workspace: weekly email digest (and its day), competitor alerts and which kinds (overtakes, new competitors, citations gained or lost), and whether email and in-app…

• get_alerts

  What's new for the brand since the user last looked: unread VisibilityKit notifications (competitor overtakes, new competitors, citations gained or lost, finished reports and audits) plus significant visibility changes from the last 7…

• get_plan_and_usage

  Show the workspace's VisibilityKit plan and how much of it is used: websites, tracked topics, prompts and competitors per plan, content credits this month, page-audit cap, subscription status and renewal date. Use for "how many topics can…

• get_team

  List the members of the brand's workspace with their roles, plus pending invitations. Invites and role changes happen in VisibilityKit (openUrl).

• get_brand_kit

  Show the agency's white-label brand kit used on client reports and answer cards: logo, primary and accent colors, "prepared by" line, report footer, and whether VisibilityKit branding is hidden. Agency accounts only.

• show_form

  Open a form in the VisibilityKit view so the user can fill in a multi-field action instead of typing every detail: add_brand, add_topic, add_competitor, generate_content, create_report, schedule_report, update_alert_settings or…

• check_ai_crawler_access

  Check whether AI crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, PerplexityBot, ClaudeBot, Google-Extended and others) are allowed to read a website according to its robots.txt, and whether the homepage needs JavaScript to render. Free…

• audit_page_for_ai

  Audit any public web page for AI search readiness: content structure, technical SEO, schema markup, AI crawlability and content quality, with a score per category, the top issues and quick wins. Free, works for any URL without an account.

• check_ai_citation

  Ask an AI search engine (Perplexity) a question and check whether it cites a given website in its answer, at what position, and which other brands it cites instead. Free with a VisibilityKit account. Use for "does AI recommend acme.com…

• check_brand_in_ai

  Ask several AI assistants (ChatGPT, Perplexity, Gemini, Grok, DeepSeek and others) about a brand name and report which ones know it, the sentiment, what they say, and a tip per engine. A quick spot check for brands not yet tracked…

• settings_read

  Read the user's VisibilityKit assistant preferences: the default brand and default time window used when a request doesn't name them.

• settings_update

  Change the user's VisibilityKit assistant preferences (default brand, default time window). Pass only the settings that change, e.g. {"set":{"defaultWindowDays":"90"}}.

• search_brands

  Typeahead search for @-mentions over the user's VisibilityKit brands, tracked topics and competitors.