The best MCP servers for AEO in 2026

check_ai_access · 383 ms · 4 November 2026, 20:26 UTC

Sent

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

Received

{
  "origin": "https://supereo.app",
  "path": "/",
  "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.

audit_page · 389 ms · 4 November 2026, 20:26 UTC

Sent

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

Received

{
  "url": "https://supereo.app/about",
  "finalUrl": "https://supereo.app/about",
  "status": 200,
  "ms": 61,
  "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": null,
    "queryInOpening": null,
    "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": []
}

get_page_diagnosis · 2,523 ms · 4 November 2026, 20:26 UTC

Sent

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

Received

{
  "url": "https://supereo.app/about",
  "finalUrl": "https://supereo.app/about",
  "status": 200,
  "problem": null,
  "kind": {
    "value": "product_landing",
    "source": "content_read"
  },
  "pageType": "product",
  "score": 84,
  "checks": [
    {
      "id": "real_text",
      "label": "Real text in the HTML (cited homepages carry about 900 words)",
      "pass": false,
      "detail": "480 words"
    },
    {
      "id": "prices_on_page",
      "label": "Prices on the page",
      "pass": true,
      "detail": "2 dollar figures"
    },
    {
      "id": "product_schema",
      "label": "Product schema",
      "pass": true,
      "detail": "JSON-LD types: Organization, Person, SoftwareApplication, Offer, UnitPriceSpecification, AboutPage, WebSite"
    },
    {
      "id": "server_rendered",
      "label": "Real text in the HTML, not a JavaScript shell",
      "pass": true,
      "detail": "480 words in the HTML"
    },
    {
      "id": "fresh",
      "label": "Updated within 30 days",
      "pass": true,
      "detail": "newest date 2026-11-04 (json_ld), 0 days old"
    },
    {
      "id": "specific",
      "label": "Specific rather than generic",
      "pass": true,
      "detail": "specificity 4 of 5, generic AI style 3 of 5"
    }
  ],
  "gaps": [
    {
      "id": "real_text",
      "label": "Real text in the HTML (cited homepages carry about 900 words)",
      "detail": "480 words"
    }
  ],
  "numbers": {
    "dollarFigures": 2,
    "percentFigures": 1,
    "newestDate": {
      "date": "2026-11-04T00:00:00.000Z",
      "source": "json_ld",
      "ageDays": 0
    }
  },
  "read": {
    "status": "done",
    "summary": "About page for supereo, an AI agent for getting brands recommended by AI engines; covers its scope, pricing (Copilot $149/mo, Autopilot $499/mo, 7-day trial), proof method and corporate ties, with no independent evidence.",
    "answersUpFront": "partly",
    "specificity": 4,
    "originalData": false,
    "sourcesCited": false
  },
  "costCents": 0.03774
}

get_fix_playbook · 268 ms · 4 November 2026, 20:26 UTC

Sent

{
  "fix_type": "crawler_rules"
}

Received

{
  "playbooks": [
    {
      "type": "crawler_rules",
      "kind": "Crawler access",
      "skill": "fix-crawler-rules",
      "description": "How supereo's engineer writes a crawler fix (crawler_rules) - robots.txt rules that let the AI crawlers the work item names read the pages it names, without changing what any search engine's crawler may read. Read it, and RUBRIC.md beside it, before you plan a crawler fix.",
      "playbook": "# Crawler fix (crawler_rules)\n\nAn AI engine can only cite a page its crawler may read. The work item names the crawlers and the paths, from its evidence: a robots.txt rule that blocks them, or no rule that lets them in. The AI crawlers supereo writes rules for: GPTBot, OAI-SearchBot and ChatGPT-User (OpenAI), ClaudeBot, Claude-SearchBot and Claude-User (Anthropic), PerplexityBot and Perplexity-User (Perplexity). This fix never writes a rule for a search engine's crawler (Googlebot, Bingbot and the rest), and never changes the `User-agent: *` group, which search engines read.\n\n## 1. Find the file the site serves\n\n- get_work_item's fence names the robots.txt you may change (public/robots.txt in Next.js and Astro). When the fence notes that code writes robots.txt instead (app/robots.ts, an Astro endpoint), a content change can't fix it: write why in plan.md, propose the code change with propose_fix, and hand the item back with hand_back.\n- fetch_as_bot the live robots.txt as one of the work item's crawlers. Compare it with the repo's file: a host or a proxy can serve something else, and the plan file says which you saw.\n\n## 2. Work out what each crawler reads today\n\nA crawler follows the one group that names it most specifically: its own `User-agent:` line if one exists, else `User-agent: *`. Within a group, the longest matching path rule wins, and Allow wins a tie. Write down, for each crawler the work item names, which group it follows today and whether each path the item names is allowed.\n\n- A work item that asks to **let crawlers in**, when every one is already allowed: the robots.txt isn't the cause. Say so in plan.md and report_progress, propose what to check instead (a firewall or a host's bot setting) with propose_fix, and hand the item back.\n- A work item that asks to **name crawlers explicitly**, each with a group of its own, is written even when `*` allows them today: an explicit group is one a later rule for `*` can't take away, and it says plainly which AI crawlers the site welcomes.\n\n## 3. Write the rules\n\n- Add one group for the crawlers the work item names (their `User-agent:` lines together), with an `Allow:` line for each path it names (`Allow: /` when it names the whole site), after the existing groups, with a one-line comment above it saying what it's for.\n- When a crawler already has its own group, change that group's lines only as far as the work item asks.\n- Keep every other line exactly as it is: the `*` group, every search engine's group, every `Sitemap:` line, comments and blank lines. A search engine's crawler must read exactly what it read before.\n- Only plain lines: `User-agent:`, `Allow:`, `Disallow:`, `# comment`, blank lines.\n\n## 4. Check it\n\n- Read the file as each crawler would, again, after your change: each crawler the item names reaches each path it names; Googlebot, Bingbot and the `*` group read exactly as before. Write both readings in plan.md.\n- Run the repo's build where it runs, so the file still ships (a robots.txt in public/ is copied as it is).\n\n## 5. Deliver\n\nfix.patch (the robots.txt change only), after/<path to robots.txt>, plan.md with both readings, and sources.md saying the change adds no number. Then end your turn for the grader."
    }
  ]
}

Trimmed: the playbook's rubric and the list of the other fix types.