Checks a website for AI agents: robots.txt, llms.txt, MCP, A2A. Ranked fixes, text to paste.
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.
Check how well a website welcomes AI agents: robots.txt rules for AI bots, llms.txt, sitemap, search indexing, title and description, A2A agent card, MCP endpoint, OpenAPI description, and whether automated visitors are blocked. Returns what is there, what is missing and how to fix it.
The website to check, for example https://example.com.
Optional: check again now instead of using a result from the last 10 minutes, for example after a fix. The answer then says what changed.
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.
claude mcp add --transport http agent-readiness https://wondaverse.com/check/mcp
Check how well a website welcomes AI agents: robots.txt rules for AI bots, llms.txt, sitemap, search indexing, title and description, A2A agent card, MCP endpoint, OpenAPI description, and whether automated visitors are blocked. Returns what is there, what is missing and how to fix it.
| Argument | Type | Description |
|---|---|---|
| url |
| string |
| The website to check, for example https://example.com. |
| fresh | boolean | Optional: check again now instead of using a result from the last 10 minutes, for example after a fix. The answer then says what changed. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The website to check, for example https://example.com."
},
"fresh": {
"type": "boolean",
"description": "Optional: check again now instead of using a result from the last 10 minutes, for example after a fix. The answer then says what changed."
}
},
"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 Oct 30, 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.