Skip to main content
Cituna
AI Visibility

The AI-visibility MCP server

Query your AI-visibility scans, gaps, rankings and Google Search Console data from Claude, or any MCP client, in plain language. Read tools are included from $39; write tools on Pro.

By Rahul AUpdated July 25, 20266 min read

See which of these you are already failing.

On this page
  1. What it does
  2. The tools Claude gets
  3. Connect it to Claude
  4. Which plan you need
  5. FAQ

Most AI-visibility tools hand you a dashboard. The Cituna MCP server hands your data to your assistant. Connect it once and Claude can read how the AI engines cite your brand, tell you exactly which buyer prompts you are losing, work your fix queue, and pull your live Google Search Console numbers, without you leaving the chat or exporting a thing.

What it does

MCP, the Model Context Protocol, is an open standard for connecting AI assistants to live data and tools. Our server implements it, so any MCP client can query your workspace directly. Point it at Claude and you can ask about the six engines we track, ChatGPT, Perplexity, Gemini, Claude, Grok and Google AI Overviews (we do not track Microsoft Copilot), with the tracking grid refreshed daily across all six.

What that looks like in practice:

  • Your visibility, on demand. “What changed in my AI visibility this week, and which engines dropped us?”
  • The receipts. “What did Perplexity actually answer for ‘best CRM for small business’, and who did it cite instead of us?”
  • The fix queue. “List the open gaps for acme.com and walk me through the schema one.”
  • Search Console, joined up. “How did acme.com do in Search over the last 28 days, broken down by country then device?”

Rare, not exclusive:

Getting an MCP from $39: paired with a native Google Search Console integration, so one assistant reads your AI-visibility gaps and your real search clicks together, is the hard part to find. Several tools now ship an MCP, so it isn’t ours alone; pairing it with Search Console at $39 is. For the full, attributed comparison, see our best AI visibility tools rundown.

The tools Claude gets

Sixteen tools ship today: twelve reads and four writes. Reads work from $39 (Starter and up), with one exception: list_keywords reads the keyword dataset that is part of Pro. The four write actions, which change your workspace, need Pro or higher.

ToolWhat Claude does with itPlan
whoamiConfirm the connection and see your account, workspace, plan and usage.From $39
list_brandsList the domains tracked in your workspace.From $39
get_visibilityRead today’s tracking grid: which of the six engines cited you, for which prompts, and at what position.From $39
get_engine_answersPull the receipts: what each engine actually answered for a prompt, and which brands it cited instead.From $39
list_auditsList recent AI-visibility audits, scores and open-gap counts, newest first.From $39
get_auditOpen one audit in full: per-engine citations and the prompt × engine matrix.From $39
list_gapsRead a domain’s fix queue, each gap and its concrete fix.From $39
gsc_statusCheck whether Google Search Console is connected and which properties are available.From $39
gsc_overviewSummarise Search Console clicks, impressions, CTR and average position for a domain.From $39
gsc_queryRun any Search Analytics query, choose dimensions, filters and a date range.From $39
list_keywordsRead keywords with real search demand and the stage of the page behind each, filter for demand nothing is written for yet.Pro
list_content_queueSee what AutoSEO already has drafted or in flight, so nothing gets queued twice.From $39
queue_articleQueue a keyword so AutoSEO drafts the page on its next run.Pro
mark_article_publishedTell Cituna a page for a keyword is live, so it stops suggesting the topic.Pro
set_gap_statusMove a gap along your queue, mark it todo, doing or done.Pro
run_scanRun a fresh AI-visibility scan for a URL (uses one scan from your quota).Pro

Reads work on Starter and up (list_keywords needs Pro's keyword data); the four write tools (queue_article, mark_article_published, set_gap_status, run_scan) require Pro or higher. The free trial does not include MCP access. Tool set as of August 4, 2026.

Connect it to Claude

Three steps, about a minute. Nothing to install, no config file and no key to copy: you approve the connection in your browser, decide there whether Claude may make changes as well as read, and can revoke it from Integrations whenever you want.

  1. Add the connector

    In Claude, open Settings → Connectors and click Add custom connector. Paste this URL:

    connector URL
    https://mcp.cituna.com/mcp
  2. Approve access

    Claude sends you to Cituna to sign in, then shows what it is asking for. Leave the write box ticked to let it run scans and work your queue, or untick it for read-only. Revoke whenever you like from Integrations. Needs Starter ($39) or higher.

  3. Ask your first question

    That is it, no terminal and nothing to install. Good openers:

    • “What changed in my AI visibility this week?”
    • “Which buyer prompts am I losing, and who gets cited instead?”
    • “Which Search Console queries lost clicks this month?”
Prefer to run it on your own machine?

The server is also on npm, which is the better fit for scripts and CI. Generate a key first (Integrations → Claude / MCP access → Generate token), then:

terminal
claude mcp add cituna --scope user \
  --env CITUNA_API_KEY=YOUR_TOKEN \
  -- npx -y cituna-mcp

Any other MCP client works too: the command is npx -y cituna-mcp with CITUNA_API_KEY in its environment. This path needs Node 18.17+ on your machine; the connector above does not.

Which plan you need

The MCP server is included on every paid plan, there is no separate add-on, and it is not part of the 3-day free trial. On Starter ($39), the read tools let Claude query your tracking grid, audits, gaps, content queue and Search Console data. Pro ($119) adds the keyword dataset and the four write tools, so Claude can start a fresh scan, work your fix queue, and queue or mark up articles for you; Max ($399) raises the scan, data and MCP allowances; and a custom Enterprise plan lifts them further with invoiced billing and priority onboarding. See the full pricing for the per-plan limits.

Drafted with AI assistance from our own research and Search Console data, and reviewed by Rahul A before publishing. Rules and prices change; check the linked official source before you act.

Frequently asked questions

What is the Cituna MCP server?

It is a Model Context Protocol (MCP) server that connects your Cituna workspace to Claude or any MCP client. Once connected, you can ask in plain language about your AI-visibility scans, the buyer prompts where you are missing, your fix queue, your rankings and your live Google Search Console data, and Claude answers from your real data instead of guessing.

Which MCP clients can I use it with?

Any MCP client. The quickest route is the hosted connector: add https://mcp.cituna.com/mcp as a custom connector, approve access in your browser, and you are connected. That path needs nothing installed, so it works in Claude on the web and on mobile as well as in Claude Desktop and Claude Code. If you would rather run the server yourself, it is also on npm as cituna-mcp and takes one line of config plus a token from the app.

Do I need Node or a terminal to connect it?

No. Adding the hosted connector is three steps in your MCP client: paste the URL, sign in to Cituna, approve access. Nothing is installed and there is no config file or API key to copy. Node 18.17 or later is only needed for the optional local install, which suits scripts and CI.

What is Cituna allowed to do once I approve it?

Whatever you tick on the approval screen, and no more. Read access covers your tracking, audits, gap queue, keywords and Search Console data. Leaving the write box ticked also lets Claude run scans, move gaps and queue articles; untick it and the connection is strictly read-only, even on a plan that allows writes. Cituna never receives your password or your Google credentials, and you can revoke the connection from Integrations at any time.

Is the MCP server included in my plan?

On every paid plan, yes. The read tools are included from the $39 Starter plan, so you can query your audits, gaps and Search Console data straight away. The two write tools, run_scan and set_gap_status, need Pro or higher; on Starter the MCP is read-only. The 3-day free trial does not include MCP access, it unlocks the moment your plan starts.

Can Claude change my data or run scans?

Only if you are on Pro or higher, and only through two clearly marked write tools: run_scan (start a fresh scan, which uses one scan from your quota) and set_gap_status (move a gap along your fix queue). Everything else is read-only. Claude acts on your behalf with the token you issue, and you can revoke that token in the app at any time. Your Google account token stays server-side, the MCP server never holds it.

See how AI engines see your brand

Start a free 3-day trial and see the exact buyer prompts you lose across ChatGPT, Perplexity, Gemini, Claude, Grok and Google AI Overviews, with a prioritized AEO, GEO and SEO action plan and the fixes to win them.

3-day free trial · Card required, cancel anytime · Works with ChatGPT, Perplexity, Gemini, Claude, Grok and Google AI Overviews

Start free trial