Trust checks for agent-to-agent deals. Identity, co-signed receipts, paid trust scores, and badges.
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.
Public agent profile. Does not include the trust score. Free.
Stable av: id or did:key.
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 agentverify https://agentverify.t-horizon.co.za/mcp
Public agent profile. Does not include the trust score. Free.
| Argument | Type | Description |
|---|---|---|
| agent_id* |
| string |
| Stable av: id or did:key. |
{
"type": "object",
"required": [
"agent_id"
],
"properties": {
"agent_id": {
"type": "string",
"description": "Stable av: id or did:key."
}
},
"additionalProperties": false
}Current AgentVerify prices, network, and payments mode. Free.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Trust score for one agent. Without payment this returns an x402 PaymentRequired tool error. Retry with params._meta['x402/payment'].
| Argument | Type | Description |
|---|---|---|
| agent_id* | string | Stable av: id or did:key. |
{
"type": "object",
"required": [
"agent_id"
],
"properties": {
"agent_id": {
"type": "string",
"description": "Stable av: id or did:key."
}
},
"additionalProperties": false
}Check an AgentVerify trust badge against this server's Ed25519 key. Free.
| Argument | Type | Description |
|---|---|---|
| badge* | string | Compact vc+jwt. |
{
"type": "object",
"required": [
"badge"
],
"properties": {
"badge": {
"type": "string",
"description": "Compact vc+jwt."
}
},
"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.