Preparación para IA · REST API

AI crawler access, llms.txt and entity signals from the last audit.

Las descripciones vienen del documento OpenAPI y están en inglés.

Parámetros

Nombre	Dónde	Detalles
`siteId`Obligatorio	ruta	stringWebsite id, from GET /sites.

Respuesta

200 · application/json

Campo	Detalles
`checkedAt`	string or null · required; When it was last checked
`robotsTxt`	ok \| missing \| error \| · required; What /robots.txt answered
`crawlers`	list of object · required
`crawlers[].bot`	string · required; Crawler user agent
`crawlers[].owner`	string · required; Company behind it
`crawlers[].purpose`	string · required; What it is used for
`crawlers[].kind`	training \| search \| both · required; What the crawler feeds: model training, AI search answers, or both
`crawlers[].allowed`	true or false or null · required; robots.txt lets it read the home page; null when robots.txt could not be read
`crawlers[].rule`	group \| default \| none · required; group: a robots.txt rule names this crawler; default: the * rules apply; none: no rule applies
`llmsTxt`	object or null · required
`llmsTxt.present`	true or false · required; A text file is at /llms.txt
`llmsTxt.url`	string · required; Address read
`llmsTxt.status`	integer or null · required; HTTP status
`llmsTxt.bytes`	integer · required; Size in bytes
`llmsTxt.checkedAt`	string or null · required; When it was read
`entity`	object or null · required; Who the website is, as AI assistants can read it
`entity.organizationSchema`	true or false · required; An Organization schema is on the website
`entity.organizationName`	string or null · required; Name in that schema
`entity.sameAs`	list of string · required; Profiles the schema links (sameAs)
`entity.aboutPage`	string or null · required; Path of the About page
`entity.contactPage`	string or null · required; Path of the Contact page
`entity.napAgrees`	true or false or null · required; Name, address and phone in the schema match the contact page; null: nothing to compare
`note`	string · required; How to read the fields
`link`	address (URL) · required; The AI readiness screen in the app

Errores

Estado	Significado
`401`	Missing, unknown or revoked key. Codes: `missing_key`, `invalid_key`.
`403`	The key lacks the scope, covers another website, or its owner lost access. Codes: `missing_scope`, `other_site`, `owner_left`, `no_owner`, forbidden.
`404`	Not found. Codes: `not_found`.
`429`	Too many requests this hour for this key. Codes: `rate_limited`.
`503`	Switched off for now. Codes: `feature_off`.

Petición de ejemplo

curl \
  -H "Authorization: Bearer mr_ws_…" \
  "https://app.monoranks.com/api/v1/sites/SITE_ID/geo"

const res = await fetch("https://app.monoranks.com/api/v1/sites/SITE_ID/geo", {
  headers: { Authorization: "Bearer mr_ws_…" },
});
if (!res.ok) throw new Error((await res.json()).error.message);
const data = await res.json();

import requests

res = requests.get(
    "https://app.monoranks.com/api/v1/sites/SITE_ID/geo",
    headers={"Authorization": "Bearer mr_ws_…"},
)
res.raise_for_status()
data = res.json()

<?php
$ch = curl_init("https://app.monoranks.com/api/v1/sites/SITE_ID/geo");
curl_setopt_array($ch, [
    CURLOPT_HTTPHEADER => ["Authorization: Bearer mr_ws_…"],
    CURLOPT_RETURNTRANSFER => true,
]);
$data = json_decode(curl_exec($ch), true);

import axios from "axios";

const { data } = await axios.get("https://app.monoranks.com/api/v1/sites/SITE_ID/geo", { headers: { Authorization: "Bearer mr_ws_…" } });

Respuesta de ejemplo

{
  "checkedAt": "2026-10-04T02:18:44.000Z",
  "robotsTxt": "ok",
  "crawlers": [
    {
      "bot": "GPTBot",
      "owner": "OpenAI",
      "purpose": "Training data for OpenAI models",
      "kind": "training",
      "allowed": false,
      "rule": "group"
    },
    {
      "bot": "OAI-SearchBot",
      "owner": "OpenAI",
      "purpose": "ChatGPT search results and citations",
      "kind": "search",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "ChatGPT-User",
      "owner": "OpenAI",
      "purpose": "Pages a ChatGPT user asks about, fetched live",
      "kind": "search",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "ClaudeBot",
      "owner": "Anthropic",
      "purpose": "Training data for Claude models",
      "kind": "training",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "Claude-SearchBot",
      "owner": "Anthropic",
      "purpose": "Improves the quality of Claude's search results",
      "kind": "search",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "Claude-User",
      "owner": "Anthropic",
      "purpose": "Pages a Claude user asks about, fetched live",
      "kind": "search",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "PerplexityBot",
      "owner": "Perplexity",
      "purpose": "Perplexity search index and citations",
      "kind": "search",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "Google-Extended",
      "owner": "Google",
      "purpose": "Gemini training and grounding (not Google Search)",
      "kind": "training",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "Applebot-Extended",
      "owner": "Apple",
      "purpose": "Apple Intelligence training",
      "kind": "training",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "CCBot",
      "owner": "Common Crawl",
      "purpose": "Open crawl used to train many models",
      "kind": "training",
      "allowed": false,
      "rule": "group"
    },
    {
      "bot": "Bytespider",
      "owner": "ByteDance",
      "purpose": "ByteDance models",
      "kind": "training",
      "allowed": false,
      "rule": "group"
    },
    {
      "bot": "meta-externalagent",
      "owner": "Meta",
      "purpose": "Meta AI training and product indexing",
      "kind": "both",
      "allowed": true,
      "rule": "default"
    },
    {
      "bot": "Amazonbot",
      "owner": "Amazon",
      "purpose": "Improves Amazon products and may train Amazon AI models",
      "kind": "both",
      "allowed": true,
      "rule": "default"
    }
  ],
  "llmsTxt": {
    "present": false,
    "url": "https://acmebikes.com/llms.txt",
    "status": 404,
    "bytes": 0,
    "checkedAt": "2026-10-04T02:18:44.000Z"
  },
  "entity": {
    "organizationSchema": true,
    "organizationName": "Acme Bikes",
    "sameAs": [
      "https://www.instagram.com/acmebikes",
      "https://www.youtube.com/@acmebikes"
    ],
    "aboutPage": "/about/",
    "contactPage": "/contact/",
    "napAgrees": true
  },
  "note": "From the last audit, or the last check after MonoRanks wrote crawler rules or llms.txt through WordPress.",
  "link": "https://app.monoranks.com/sites/3f6c2a1e-8b4d-4c7a-9e21-5d0b7a6f4c13/geo"
}

{
  "error": {
    "code": "missing_key",
    "message": "Send the key as Authorization: Bearer mr_site_…"
  }
}

{
  "error": {
    "code": "missing_scope",
    "message": "This key does not have the scope this call needs."
  }
}

{
  "error": {
    "code": "not_found",
    "message": "Website not found."
  }
}

{
  "error": {
    "code": "rate_limited",
    "message": "More than 1200 requests this hour for this key."
  }
}

{
  "error": {
    "code": "feature_off",
    "message": "AI readiness is switched off for now."
  }
}

El servidor MCP hace lo mismo con la herramienta geo_access.