Growthr SEO + GEO MCP

Fetch a public domain the way search engines and AI crawlers do (ChatGPT's GPTBot, Claude's ClaudeBot, and the fetchers behind Perplexity and Google AI Overviews: from a datacenter IP, no JavaScript) and run 22 weighted checks: reachability as a browser, GPTBot, and ClaudeBot; server-rendered content; metadata; strict JSON-LD and Organization schema; robots.txt access for AI crawlers; llms.txt and an in-page link to it; sitemap; honest 404s; markdown negotiation; trust pages; speed; and on-page SEO (title, description, single h1, viewport, alt text, favicon). Returns a 0-100 score and every check with pass/fail, what was found, and a fix hint. Reads about a dozen public URLs once. Growthr logs the domain and tool name for usage stats.

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Public domain, e.g. example.com (no path)"
    }
  },
  "required": [
    "domain"
  ]
}

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "score": {
      "type": "integer",
      "description": "0-100"
    },
    "checks": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "label": {
            "type": "string"
          },
          "pass": {
            "type": "boolean"
          },
          "detail": {
            "type": "string"
          },
          "weight": {
            "type": "number"
          }
        },
        "required": [
          "id",
          "label",
          "pass"
        ]
      }
    },
    "throttledCount": {
      "type": "integer",
      "description": "Requests the site answered with HTTP 429"
    }
  },
  "required": [
    "domain",
    "score",
    "checks"
  ]
}

Read a site's homepage, sitemap (or homepage links), and up to twelve pages, then draft an llms.txt in the llmstxt.org format: H1 name, blockquote summary, grouped page list with one-line descriptions, contact, profiles, links. The 'When to use' section is left as a marked placeholder on purpose; it is a judgment about the business that no crawler can write. Returns the draft plus notes on anything skipped.

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Public domain, e.g. example.com"
    }
  },
  "required": [
    "domain"
  ]
}

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "pages": {
      "type": "integer",
      "description": "Pages read"
    },
    "notes": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "llmsTxt": {
      "type": "string",
      "description": "The draft, llmstxt.org format"
    }
  },
  "required": [
    "domain",
    "llmsTxt"
  ]
}

Run the scan and sort every failed check into buckets: blockers (fix before anything else, they hide everything downstream), this afternoon (metadata, llms.txt, trust pages, on-page), needs a sprint (schema, markdown negotiation, speed), and the off-site work no scan can measure (reviews, directories, third-party mentions), which is what decides whether AI engines recommend a business.

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Public domain, e.g. example.com"
    }
  },
  "required": [
    "domain"
  ]
}

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "score": {
      "type": "integer"
    },
    "blockers": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Check ids to fix before anything else"
    },
    "afternoon": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "sprint": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "other": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "domain",
    "score",
    "blockers",
    "afternoon",
    "sprint"
  ]
}

Run one buyer-shaped prompt through Gemini with Google Search grounding (a real, cited web search, the same mechanism behind Google AI Overviews) and report where the brand lands on the five-rung ladder: absent, cited (a page of the brand's site is a source), mentioned (named in the text), recommended (on the shortlist), or recommended against. Also returns the other names on the shortlist and the source domains the answer was built from. One prompt per call; limited to a few calls per day per user because grounded requests are billed per query.

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "The question a buyer would ask, e.g. 'best corporate event photographer in New York'"
    },
    "brand": {
      "type": "string",
      "description": "Brand name to look for, e.g. 'Growthr'"
    },
    "domain": {
      "type": "string",
      "description": "Optional brand domain, e.g. growthr.com, to detect citations"
    }
  },
  "required": [
    "prompt",
    "brand"
  ]
}

{
  "type": "object",
  "properties": {
    "rung": {
      "type": "string",
      "enum": [
        "absent",
        "cited",
        "mentioned",
        "recommended",
        "recommended against"
      ]
    },
    "cited": {
      "type": "boolean"
    },
    "mentioned": {
      "type": "boolean"
    },
    "recommended": {
      "type": "boolean"
    },
    "against": {
      "type": "boolean"
    },
    "shortlist": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Providers the answer put forward"
    },
    "shortlistSource": {
      "type": "string",
      "enum": [
        "llm",
        "heuristic"
      ]
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Source domains the answer was built from"
    },
    "engine": {
      "type": "string"
    }
  },
  "required": [
    "rung",
    "shortlist",
    "sources",
    "engine"
  ]
}