Check if AI crawlers can read a site, and the questions customers ask AI about a business.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Builds the questions a customer is likely to ask an AI assistant (in Hebrew) before choosing a business of a given type, grouped by stage of the buying journey: the problem, comparing options, choosing a provider, price, trust and after the purchase. Use when a business owner wants to know what customers ask ChatGPT or Claude about their field, city or services.
Type of business, in Hebrew if possible, e.g. "מרפאת שיניים" or "עורך דין לדיני עבודה"
City or area, optional
Who the customers are, optional
Up to 3 main services, optional
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http spotted https://spotted.elya-studio.com/mcp
Builds the questions a customer is likely to ask an AI assistant (in Hebrew) before choosing a business of a given type, grouped by stage of the buying journey: the problem, comparing options, choosing a provider, price, trust and after the purchase. Use when a business owner wants to know what customers ask ChatGPT or Claude about their field, city or services.
| Argument | Type | Description |
|---|---|---|
| city | string | City or area, optional |
| kind* | string | Type of business, in Hebrew if possible, e.g. "מרפאת שיניים" or "עורך דין לדיני עבודה" |
| audience | string | Who the customers are, optional |
| services | array | Up to 3 main services, optional |
{
"type": "object",
"required": [
"kind"
],
"properties": {
"city": {
"type": "string",
"description": "City or area, optional"
},
"kind": {
"type": "string",
"description": "Type of business, in Hebrew if possible, e.g. \"מרפאת שיניים\" or \"עורך דין לדיני עבודה\""
},
"audience": {
"type": "string",
"description": "Who the customers are, optional"
},
"services": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 3,
"description": "Up to 3 main services, optional"
}
},
"additionalProperties": false
}Checks one public web page the way AI crawlers do: reads its robots.txt, meta robots / X-Robots-Tag and /llms.txt, and reports, for each AI and search crawler (OpenAI, Anthropic, Perplexity, Google, Microsoft), whether it is allowed to read that page. Use when someone asks whether ChatGPT, Claude, Perplexity or Google AI can see, read or cite their site. Facts only, no score.
| Argument | Type | Description |
|---|---|---|
| url* | string | The page to check, e.g. example.co.il or https://example.com/services |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The page to check, e.g. example.co.il or https://example.com/services"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 12, 2026.