supereo_
Get started

guide // how to // 2026

Can Claude Code do GEO? Yes, with an MCP server

Yes, once it has the tools. Claude Code already reads and edits your code. Connected to supereo's MCP server it can also check which AI crawlers may read your site, fetch a page as ChatGPT's search crawler, audit the page the way AI engines read it, and then write the fix in your repo. Claude Code connects to remote MCP servers over HTTP and signs in from /mcp[1][2]. supereo is our pick, and we make it: it does the rest of GEO too, off your site, and proves each move against control questions. In the real run below, Claude Code called three of supereo's tools: check_ai_access, fetch_as_bot and audit_page.

Updated . Prices checked 7 November 2026.

The verdict

  1. GEO from Claude Code, done and proven

    supereoour pick, and we make it

    • best for teams that want AEO done, not a dashboard: supereo does everything it takes to get you recommended, from your site and pages to the roundups, placements and videos AI reads;
    • it proves each move against control questions, with sample sizes and ranges on every number;
    • run it from Claude or ChatGPT: an MCP server with the same tools supereo's own agent uses.

    From $149 a month

    Run the free auditFree, no card, every answer shown.

The steps

  1. Add supereo's MCP server

    In your project, run: claude mcp add --transport http supereo https://supereo.app/api/mcp. HTTP is the transport Claude Code's docs recommend for remote servers[1].

  2. Sign in with /mcp

    Run /mcp in Claude Code and sign in to supereo with the code it emails you[2]. Your first sign-in makes your account, and the free tools work at once.

  3. Check what AI crawlers may read

    Ask Claude Code to check your site. check_ai_access reads your robots.txt and llms.txt and says, for each AI crawler, whether it may read the page.

  4. Read a page as an AI crawler

    fetch_as_bot fetches a URL as one crawler, such as OAI-SearchBot, ChatGPT's search crawler. audit_page lists what a crawler without JavaScript gets: the title, headings, words, tables, dates and structured data.

  5. Fix it in your repo

    Claude Code edits your code as it always does. For a fix supereo knows, get_fix_playbook gives the playbook supereo's own engineer follows, so the change is written the same way.

  6. Prove it worked

    AI answers move from one run to the next, so one before and after can't show a gain. On a plan, register the change as a test before it ships with create_experiment, log it once it is live with log_change, and get_experiment gives its verdict against control questions.

Real runs

a real run // 4 November 2026

Claude Code checks supereo.app with supereo's MCP server

Recorded from supereo's MCP server on its staging environment, https://staging.supereo.app/api/mcp. 3 calls. Session: Claude Code 2.1.299, claude-opus-5-5, started with --bare and no built-in tools, supereo's MCP server its only one.

The prompt, as typed

Use supereo to check whether AI crawlers can read supereo.app, then look at https://supereo.app/about the way ChatGPT's search crawler sees it, and tell me what to fix first so AI answers cite it. Keep the answer short.

check_ai_access · 360 ms ·

Sent

{
  "url": "https://supereo.app/about"
}

Received

{
  "origin": "https://supereo.app",
  "path": "/about",
  "robotsTxt": {
    "status": "ok",
    "detail": "robots.txt read."
  },
  "crawlers": [
    {
      "bot": "GPTBot",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "*"
    },
    {
      "bot": "OAI-SearchBot",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "OAI-SearchBot"
    },
    {
      "bot": "ChatGPT-User",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "*"
    },
    {
      "bot": "ClaudeBot",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "*"
    },
    {
      "bot": "Claude-SearchBot",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "Claude-SearchBot"
    },
    {
      "bot": "Claude-User",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "*"
    },
    {
      "bot": "PerplexityBot",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "PerplexityBot"
    },
    {
      "bot": "Google-Extended",
      "aiCrawler": true,
      "allowed": true,
      "rule": "Allow: /",
      "group": "*"
    },
    {
      "bot": "Googlebot",
      "aiCrawler": false,
      "allowed": true,
      "rule": "Allow: /",
      "group": "Googlebot"
    },
    {
      "bot": "Bingbot",
      "aiCrawler": false,
      "allowed": true,
      "rule": "Allow: /",
      "group": "Bingbot"
    }
  ],
  "llmsTxt": {
    "served": true,
    "status": 200,
    "chars": 1870
  },
  "edge": {
    "connected": false,
    "days": 7,
    "blockedFromOperatorAddresses": [],
    "spooferDenials": 0,
    "note": "Not connected yet. This needs supereo to read the site's own traffic at Cloudflare or Vercel: connect it at /dashboard/reads/connect in supereo."
  },
  "note": "From robots.txt and llms.txt alone. A block at the site's CDN or firewall, or an answer that depends on the crawler's address, shows only in its traffic."
}

Trimmed: llmsTxt's excerpt of the file, which supereo.app/llms.txt serves in full.

fetch_as_bot · 190 ms ·

Sent

{
  "url": "https://supereo.app/about",
  "bot": "OAI-SearchBot",
  "max_html_chars": 20000
}

Received

{
  "url": "https://supereo.app/about",
  "finalUrl": "https://supereo.app/about",
  "bot": "OAI-SearchBot",
  "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36; compatible; OAI-SearchBot/1.4; +https://openai.com/searchbot",
  "status": 200,
  "htmlChars": 38005,
  "truncated": true,
  "ms": 28,
  "redirects": [],
  "note": "What the site served this user agent from supereo's address. A site that checks crawler IP addresses may answer the real crawler differently."
}

Trimmed: the HTML the crawler received and the response headers: the page itself, as supereo.app/about serves it.

audit_page · 239 ms ·

Sent

{
  "url": "https://supereo.app/about",
  "query": "What is supereo?"
}

Received

{
  "url": "https://supereo.app/about",
  "finalUrl": "https://supereo.app/about",
  "status": 200,
  "ms": 47,
  "signals": {
    "title": "About supereo · the AI agent that gets your brand recommended by AI",
    "titleYear": null,
    "h1": "About supereo",
    "h1Count": 1,
    "words": 480,
    "jsShell": false,
    "h2": 6,
    "h3": 0,
    "questionHeadings": 5,
    "listItems": 16,
    "orderedListItems": 0,
    "tables": 0,
    "externalLinks": 5,
    "dollarFigures": 2,
    "percentFigures": 1,
    "bestForLabels": 3,
    "structuredData": [
      "Organization",
      "Person",
      "SoftwareApplication",
      "Offer",
      "UnitPriceSpecification",
      "AboutPage",
      "WebSite"
    ],
    "author": null,
    "newestDate": {
      "date": "2026-11-04T00:00:00.000Z",
      "source": "json_ld",
      "ageDays": 0
    },
    "noindex": false,
    "canonical": "https://supereo.app/about",
    "queryInTitle": 1,
    "queryInOpening": 1,
    "openingText": "supereo (supereo.app) is an AI agent that does everything it takes to get your brand recommended by ChatGPT, Gemini, Perplexity, Claude and Google, on your site and off it: site fixes, new pages, roun",
    "aiCrawlersBlocked": [],
    "llmsTxtServed": true
  },
  "issues": []
}

Claude Code's reply, in full

**Crawler access is fine.** robots.txt lets every AI crawler supereo checks fetch `/about`: GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot and Google-Extended, plus Googlebot and Bingbot. The site also serves an llms.txt with the right summary and prices.

**What ChatGPT's search crawler (OAI-SearchBot) gets from /about:** a 200 in 28 ms, already rendered on the server, so it doesn't depend on JavaScript. It gets the full text, about 480 words, and the page audit found nothing wrong:
- One H1 and six H2 sections, and the first sentence says what supereo is.
- The page states facts a crawler can check: the $149 and $499 prices, the 7-day trial, the founder, the parent company, and the three look-alike names it isn't.
- Its structured data covers Organization, SoftwareApplication with the prices, AboutPage and Person.
- It's dated 4 Nov 2026, the canonical points to itself, and there's no noindex tag.

**Fix first:** the brand's own `"sameAs": []` is empty in both the Organization and SoftwareApplication data. Only the founder has profiles linked. The page's main job is to tell supereo apart from SuperEA, Superego and Supereo LTD, and right now nothing outside supereo.app backs that up. Add supereo's own profiles to `sameAs`, such as a LinkedIn company page, X, GitHub, Product Hunt, G2 or Crunchbase, and link them on the page too. If those profiles don't exist yet, set them up.

**Next:**
1. **Get mentioned on other sites.** The page is already in good shape, so editing it further won't add much. AI answers cite pages that other sites point to. `backlink_gap` lists the "best X" roundups the engines read that don't name supereo yet; getting onto those is the next step.
2. **Connect Vercel in supereo** (/dashboard/reads/connect). My fetch came from supereo's own address, so it can't rule out the real OAI-SearchBot being blocked at your edge. Connecting shows confirmed crawler reads and any blocks.

Claude Code chose each call from the prompt, read the answers and wrote the reply. supereo's tools did the reading, from the open web, and Claude Code had no other tool.

What GEO means in Claude Code

GEO, generative engine optimization, is the work of getting your site read, cited and recommended in AI answers. Claude Code works on your repo, so the part it can do is the part on your site: crawler access, pages AI can read without JavaScript, answers up front, comparison and pricing pages, structured data.

What your repo can't tell it is how AI engines read your live site. That is what an MCP server adds: Claude Code can connect to outside tools and data sources this way[3], and supereo's tools read the live site the way AI crawlers do.

Where Claude Code stops

Being named in AI answers also depends on other sites: the lists, reviews and threads the engines read. Claude Code can draft a pitch, but it can't get you onto those pages.

supereo works on that part too: it finds the lists and threads worth a pitch and drafts each one for you to send, beside the work on your site, and proves each move against control questions: How supereo measures.

Have it done: supereo

01supereoour pick, and we make it

  • best for teams that want AEO done, not a dashboard: supereo does everything it takes to get you recommended, from your site and pages to the roundups, placements and videos AI reads;
  • it proves each move against control questions, with sample sizes and ranges on every number;
  • run it from Claude or ChatGPT: an MCP server with the same tools supereo's own agent uses.

From $149 a month

  • Does the worksupereo writes those pages for you, aimed at the questions where AI skips you. supereo.app
  • Proves it against controlsEach change targets a set of questions, and we compare them with a matched set the change can't affect. supereo.app
  • Runs from Claude or ChatGPTRun the same loop from Claude, Cursor or Codex. Your agent gets every tool supereo's own agent uses: your buyers' questions, every answer, the pages AI cites, your brand facts. supereo.app
  • Free auditFree · about 2 minutes · no card supereo.app
PlanA monthPromptsAI engines
Copilot$14940ChatGPT, Google AI Overviews, Google AI Mode, Gemini, Perplexity, Claude
Autopilot$49940ChatGPT, Google AI Overviews, Google AI Mode, Gemini, Perplexity, Claude

Prices from supereo.app, checked 7 November 2026. What it does, from its own pages, checked 5 November 2026.

How the proof works, with every number it runs on: How supereo measures.

Questions

Can Claude Code do GEO?

Yes, with the right tools. Connected to supereo's MCP server it checks AI crawler access, reads pages as AI crawlers do and audits them, then fixes your code. The real run above shows a session from prompt to reply.

What do I need to run GEO from Claude Code?

Claude Code and supereo's MCP server, added with claude mcp add and signed in from /mcp[2]. The free tools need no plan.

Is the run on this page real?

Yes. It is a recorded Claude Code session with supereo's MCP server and no other tool: the prompt as typed, each call as Claude Code made it, each answer as the server returned it, and Claude Code's reply in full.

Can Claude Code track AI visibility over time?

Not on its own: tracking means asking the engines the same questions on a schedule. supereo's tracked questions do that, and its MCP tools bring the results into Claude Code.

How we compiled this

Where this page's words say how an AI engine finds, reads or cites pages, the sentence links the engine's own documentation, or another source, and the day it was read.

The runs are real calls to supereo's MCP server on its staging environment, made as a house account, recorded as they happened: the arguments as sent, each answer as the client received it, its JSON indented and trimmed only where it says so, the time each call took and when it ran. A Claude Code session ran with supereo's MCP server and no other tool, and its reply is shown in full.

We make supereo, so it is the one tool this page names as a pick.

How supereo measures its own results, with every number it runs on: How supereo measures.

supereo (supereo.app) is an AI agent that does everything it takes to get your brand recommended by ChatGPT, Gemini, Perplexity, Claude and Google, on your site and off it: site fixes, new pages, roundups, placements and video. It proves what worked against control questions. Made by superagnt.

Sources

  1. HTTP servers are the recommended option for connecting to remote MCP servers. code.claude.com, read 4 November 2026.
  2. Use /mcp to authenticate with remote servers that require OAuth 2.0 authentication code.claude.com, read 4 November 2026.
  3. Claude Code can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP), an open source standard for AI-tool integrations. code.claude.com, read 4 November 2026.