Rankwise MCP server

• Registry namecom.tryrankwise/rankwiseverified in the MCP registry

The registry name sits under tryrankwise.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-20
• Tools49
• Server calls itselfrankwise-mcp
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 1280 ms.

• Its tools do every use case we checked: publish a daily sourced article to a blog; check whether ChatGPT and Perplexity name your company; review and approve drafts before they go live.
• Checked on 2 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: 2 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring2 of the 7 daily checks it takes to print a share
• Median first answer1711 ms
• Space in an agent's context≈ 8,166 tokensthe definitions of all its tools (49), which an agent carries on every turn
• Tool definitionsA · 92 of 100
• Typed results43 of 49 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 23 of 49

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →

• search_rankwise_content

  Search Rankwise's public library: guides, glossary terms, comparisons, free SEO and AI visibility tools, the AI crawler directory (GPTBot, ClaudeBot and others) and the AI engine pages. Returns matching titles with canonical URLs.

• list_rankwise_sitemaps

  List the sitemap URLs exposed by Rankwise so agents can enumerate indexable content.

• check_ai_crawler_access

  Check whether AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and others) are allowed or blocked by a website's robots.txt. Returns each crawler's status.

• score_ai_visibility

  Score how ready a website's homepage is to be found and cited by AI search engines (crawler access, structured data, content signals). Returns a score, issues and quick wins. This is an on-page readiness check, not a measurement of real…

• check_citation_readiness

  Check whether a single page is easy for AI engines to quote and cite: clear answers, headings, metadata, authorship and freshness signals. Returns findings for that page.

• get_free_ai_audit_link

  Get the link to Rankwise's free AI visibility audit for a domain. The audit checks AI crawler access and technical readiness, and runs live Perplexity queries to see whether the brand is cited. The user opens the link to run it; this tool…

• get_workspace

  Show the Rankwise workspace this connection acts in: its name, kind (personal or agency client), your role in it, and the permissions this connection has. Every other account tool works inside this one workspace.

• get_plan_and_credits

  Show the workspace's billing plan, its credit balance, what one approved brief costs in credits, and the plan limits (domains, questions, AI engines, monthly AI checks). Use it before a tool that spends credits or a plan allowance. A plan…

• list_sites

  List the site this connection reaches: its id (the workspace id), name, tracked domains, and whether automatic articles are on, how many a week, and whether they are paused. A connection reaches one site; connect again (or add a CLI…

• pause_site

  Pause automatic articles for the site. While paused nothing runs on its own: no planner fill, no drafting, no publishing, no credits used. Manual actions still work. Resume with resume_site.

• resume_site

  Resume automatic articles for the site after a pause. Cards left on days that passed move to the next free publishing days. Resuming is free.

• create_checkout_link

  Create a Stripe Checkout link for a self-serve Rankwise plan (starter, growth or scale) for this workspace's account, and give it to the person. Nothing is charged by this call: the person opens the link and pays in their browser. If the…

• list_domains

  List the domains this workspace tracks for AI visibility, with each domain's id, composite visibility score (0 to 100, null when not scored yet), number of tracked questions, how many questions AI engines mention the brand for, and the…

• add_domain

  Start tracking a domain's AI visibility in this workspace. Rankwise seeds the homepage and crawls and scores it in the background. Fails when the plan's domain limit is reached. Free: it uses no credits.

• recrawl_domain

  Queue a fresh crawl and re-score of a tracked domain's pages. It runs in the background and takes a few minutes; read get_scorecard afterwards. Free: it uses no credits.

• remove_domain

  Stop tracking a domain and permanently delete its questions, AI answers, scores and history. This cannot be undone.

• list_questions

  List the questions tracked for a domain (the prompts Rankwise asks AI engines), each with its id, market locale, and the latest check result: cited, not_cited or error, the citation position and when it ran.

• add_question

  Track a new question for a domain, e.g. "best invoicing software for freelancers". Scheduled checks then ask the plan's AI engines whether they cite the brand. Fails at the plan's question limit. Free: it uses no credits.

• remove_question

  Stop tracking a question and delete its check history. This cannot be undone.

• get_scorecard

  Read a domain's AI Visibility Scorecard: the composite score (0 to 100, null when nothing is measured yet) and the latest score, confidence and recommendations for each dimension.

• list_citations

  For each tracked question and AI engine, show the latest real measurement: whether the engine cited the brand, at which position, which URLs it cited, and when. An engine that failed to answer is skipped rather than counted as not cited.

• get_share_of_voice

  Read a domain's latest AI Share of Voice snapshot: the brand's share of AI answers, its own citations and mentions, the competitor leaderboard, and up to 12 earlier snapshots. Null when it was never measured.

• list_visibility_events

  List recent AI visibility events in the workspace, newest first: citations won and lost, fixes proposed, goals reached. Optionally only since a date or for one domain.

• run_citation_check

  Ask the plan's AI engines one tracked question now and record whether each cites the brand. Engines checked in the last few hours are served from that result at no cost. Uses the workspace's monthly on-demand check allowance. Send a…

• refresh_share_of_voice

  Capture a fresh AI Share of Voice snapshot for a domain from DataForSEO LLM Mentions. A snapshot from the last 12 hours is returned instead of buying a new one, because the index lags by days. Send a unique idempotency_key, and the same…

• list_opportunities

  List the workspace's ranked content opportunities: topics where AI engines answer questions the brand is not cited for, scored by demand, citation gap and feasibility. Dismissed topics are left out. Each item says whether a brief or…

• refresh_opportunities

  Recompute the workspace's opportunity queue from its tracked questions and AI citation data, and look for new topics. Uses paid search and AI data, so it runs at most once every 10 minutes per workspace. Send a unique idempotency_key…

• dismiss_opportunity

  Remove one topic from the workspace's opportunity queue. It can be restored in the Rankwise app (Demand page). Nothing is deleted.

• list_briefs

  List the workspace's content briefs, newest first: drafts waiting for approval (including ones Rankwise suggested), approved pieces being written, and finished ones. Filter by status. An expert sees only the briefs assigned to them.

• get_brief

  Read one brief in full: title, topic, intent, target questions, outline, research notes, suggested sources, status, and the draft article once it exists.

• create_brief

  Create a draft brief for an article. Nothing is written or charged until the brief is approved with approve_brief. If tracked_domain_id is left out, the workspace's first tracked domain grounds the brief.

• update_brief

  Edit a draft brief before it is approved: title, topic, intent, target questions or outline. An approved brief cannot be edited; edit its draft article in the app instead.

• archive_brief

  Remove a draft brief that was never approved. Approved briefs cannot be archived because their credits were spent. The brief can be restored in the app, and its topic goes back to the opportunity queue.

• approve_brief

  Approve a draft brief. This debits the workspace's credits (see get_plan_and_credits for the cost) and starts writing the AI draft article, which then waits for review; nothing is published. Re-approving a draft whose generation failed is…

• list_articles

  List the articles in this workspace, newest first: title, status (generating, ready, published, failed), publish status and published URL. Experts see only the drafts assigned to them. Filter by status or title words.

• get_article

  Read one article in this workspace: its metadata, status, meta description, the first 4,000 characters of its text (or the full HTML with include_html), the sources it cites, and the Article and FAQ structured data (JSON-LD) that ships…

• generate_article

  Write a new AI article for a keyword. It uses the same research-and-cite writer as Autopilot: real sources, links only to pages that exist, a closing call to action, and Article and FAQ schema. This spends workspace credits (1 for short…

• publish_article

  Publish one article to the workspace's connected CMS (WordPress, WordPress.com, Shopify, Webflow, Wix, Ghost, Notion, Framer or a self-hosted site). This makes it live on the customer's website. A brief draft must be approved by its…

• replace_article

  Replace an article's title, meta description, slug or full HTML body. Send only the fields to change. The slug must be unique in the workspace. Open tracked changes are dropped when the body changes. A published article's live post is not…

• bulk_replace_articles

  Replace up to 50 articles in one call, with the same rules as replace_article. Each article succeeds or fails on its own; the result lists both.

• get_autopilot

  Show the workspace's content autopilot: its mode (off, draft_only, requires_approval, full_auto), weekly article quota, whether it is paused, the plan's quota ceiling, suggestions waiting for a decision, and the upcoming approval days.

• set_autopilot

  Change the workspace's content autopilot. mode: off, draft_only (only suggests briefs, spends nothing) or requires_approval (approves up to the weekly quota of suggested briefs, which spends credits, and holds every draft for review)…

• get_planner

  Read the Content Planner: one card per publishing day with its title, keyword, article type, state (planned, writing, review, published, failed), and search volume and difficulty when measured. Defaults to the window the planner page…

• move_planner_card

  Move a card that is not written yet to another publishing day. If another unwritten card holds that day, the two swap. A day held by an article that is being written or is published is refused. Free.

• list_keywords

  List the keywords in the Content Planner, one per card, with the article title, its day, state, and search volume and difficulty when measured. Filter by state. To export them as CSV, call GET /api/v1/keywords?format=csv.

• add_keywords

  Add up to 50 keywords to the Content Planner. Each becomes a card. With a day it takes that day (an unwritten card there moves to the next free day); without one it takes the next free publishing day. Keywords already planned are skipped…

• get_search_console_summary

  Read the site's Google Search Console numbers for the last 28 days: total clicks and impressions, and the best articles by clicks. connected is false until Search Console is connected and has synced once.

• list_fixes

  List the on-page fixes Rankwise proposes for a domain (structured data, head tags, robots rules and similar), each with the page pattern it targets, the dimension it improves, why, and its status. Rankwise does not change the site; the…

• preview_fixes

  Show the exact change each proposed fix would make to the domain's pages, as a before and after diff. A dry run: it reads the live pages and changes nothing.