Agent trust verification over x402: Ed25519 fail-closed ATC/1.0, 0.01 USDC/verify, Base mainnet.
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.
Verify 1..10 Agent Trust Cards. Paid resource: 0.08 USDC via x402.
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 uta-trust-api https://uta-trust-api.eddyflores100.workers.dev/mcp
Verify 1..10 Agent Trust Cards. Paid resource: 0.08 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| cards | array |
{
"type": "object",
"properties": {
"cards": {
"type": "array",
"items": {
"type": "object"
}
}
}
}Verify one Agent Trust Card (ATC/1.0). Paid resource: 0.01 USDC via x402 — POST /v1/trust/verify with X-PAYMENT header.
| Argument | Type | Description |
|---|---|---|
| card | object | Agent Trust Card object |
{
"type": "object",
"properties": {
"card": {
"type": "object",
"description": "Agent Trust Card 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 17, 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.