Know-Your-Endpoint MCP firewall: checks uptime, Rug-Pull mutations, poisoning & x402 traps.
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.
Query live runtime KYE trust score, Rug-Pull mutation status, and safe fallback before calling external MCP/API.
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 agenttrust-kye https://agenttrust-kye-edge-gateway.a2a-data-matrix.workers.dev/mcp
Query live runtime KYE trust score, Rug-Pull mutation status, and safe fallback before calling external MCP/API.
| Argument | Type | Description |
|---|
| endpoint* | string |
{
"type": "object",
"required": [
"endpoint"
],
"properties": {
"endpoint": {
"type": "string"
}
}
}Scan MCP tool definitions for prompt injection, credential exfiltration & Unicode smuggling.
| Argument | Type | Description |
|---|---|---|
| tools* | array |
{
"type": "object",
"required": [
"tools"
],
"properties": {
"tools": {
"type": "array",
"items": {
"type": "object"
}
}
}
}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 18, 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.