Audit any URL for GEO readiness, JSON-LD schemas, and AI crawler robots.txt permissions.
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.
Run a live Generative Engine Optimization (GEO) audit on any URL: checks HTTPS, response time, JSON-LD schemas, headings, and AI crawler robots.txt permissions (GPTBot, ClaudeBot, PerplexityBot, Google-Extended).
Full URL to audit (e.g. "https://example.com").
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http geo-audit https://geooptimizer.tech/api/mcp
Run a live Generative Engine Optimization (GEO) audit on any URL: checks HTTPS, response time, JSON-LD schemas, headings, and AI crawler robots.txt permissions (GPTBot, ClaudeBot, PerplexityBot, Google-Extended).
| Argument | Type | Description |
|---|---|---|
| url |
| string |
| Full URL to audit (e.g. "https://example.com"). |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Full URL to audit (e.g. \"https://example.com\")."
}
}
}Inspect a domain robots.txt policy for major AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Applebot).
| Argument | Type | Description |
|---|---|---|
| domain* | string | Domain name (e.g. "example.com"). |
{
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"description": "Domain name (e.g. \"example.com\")."
}
}
}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 21, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.