AgentVerify
Trust checks for agent-to-agent deals. Identity, co-signed receipts, paid trust scores, and badges.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'get_agent_profile' description lacks action verbin get_agent_profile
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"agentverify": {
"url": "https://agentverify.t-horizon.co.za/mcp"
}
}
}Remote endpoints
https://agentverify.t-horizon.co.za/mcpstreamable-httpWhat it can do
Tool inventory
Tools (4)
🟢get_pricing
Current AgentVerify prices, network, and payments mode. Free.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_agent_profile(agent_id)
Public agent profile. Does not include the trust score. Free.
Input Schema
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "Stable av: id or did:key."
}
},
"required": [
"agent_id"
],
"additionalProperties": false
}🟢verify_badge(badge)
Check an AgentVerify trust badge against this server's Ed25519 key. Free.
Input Schema
{
"type": "object",
"properties": {
"badge": {
"type": "string",
"description": "Compact vc+jwt."
}
},
"required": [
"badge"
],
"additionalProperties": false
}🟢trust_check(agent_id)
Trust score for one agent. Without payment this returns an x402 PaymentRequired tool error. Retry with params._meta['x402/payment']. A registered agent can instead pass params._meta['agentverify/auth'] ({agent_id, ts, signature} over agentverify:free:v1, method MCP, path mcp:trust_check) until the daily free quota.
Input Schema
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "Stable av: id or did:key."
}
},
"required": [
"agent_id"
],
"additionalProperties": false
}Community
Evidence