# TrustAgent Agent Search

> TrustAgent Agent Search is a paid API for AI agents from trust-agent.io, paid per call via x402, $0.005001/call, status unknown (last checked 2026-09-13).

Searches the live ERC-8004 agent registry on Base by skill, domain, or name to return only agents that are currently responding, along with their endpoints and payout wallets

## Facts

- Endpoint: GET https://trust-agent.io/v1/search/agents
- Price: $0.005001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/trustagent-agent-search-5aee3da3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0jZsgoM6uqUm_TlXVq3XF

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability trustagent-agent-search-5aee3da3
```

Example prompt: Search the TrustAgent registry for live agents on Base that have declared natural-language-processing skills and also accept x402 payments — give me their names, endpoints, and payout wallets.

## When to prefer this

Use this endpoint when you need to discover live, reachable ERC-8004 agents on the Base chain that have declared specific skills or domains, rather than crawling tens of thousands of on-chain registration files yourself. It is the right choice when you need both a filtered capability match and liveness confirmation in one call, especially when building agent-of-agents workflows or automated procurement pipelines that need to pay agents via x402.

## Known failure modes

- Missing all three required search fields (skill, domain, q) — returns 400 Bad Request
- Unsupported chain value (only 'base' is served) — returns 400 or empty result
- No live agents match the query — returns empty agents array with matches: 0
- Invalid or expired cursor — pagination fails or restarts from beginning
- Service unavailable or rolling sweep in progress — may return stale or partial results

## How this service works

Which live agents can do X — and which of them are safe? Searches the skills, domains and names ERC-8004 agents declare, across the registrations this service sweeps continuously, and returns only the ones answering. Each row carries the endpoint to call, the wallet a payment reaches, and that wallet's risk band and sanctions verdict, so choosing between candidates is one call rather than a screening per row. Free alternative: GET /v1/search. Trial: 3 free calls/wallet/24h — https://trust-agent.io/v1/trial.

## Output

A paginated list of live ERC-8004 agents matching the query. Each row includes agentId, identifier, name, description, service endpoint URL, declared skills, declared domains, x402 support flag, payout wallet address, and a checkedAt liveness timestamp. Also returns total match count and a nextCursor for pagination.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "q": {
       "type": "string",
       "description": "OPTIONAL. Case-insensitive substring over the agent name; descriptions are not indexed."
      },
      "chain": {
       "type": "string",
       "description": "OPTIONAL. Only \"base\" is served."
      },
      "skill": {
       "type": "string",
       "description": "One of `skill`, `domain` or `q` is REQUIRED. Declared skill, e.g. natural-language-processing-info. GET /v1/search lists the live vocabulary."
      },
      "cursor": {
       "type": "string",
       "description": "OPTIONAL. Offset from a previous response’s nextCursor."
      },
      "domain": {
       "type": "string",
       "description": "OPTIONAL. Declared domain, e.g. compliance."
      },
      "acceptsX402": {
       "type": "string",
       "description": "OPTIONAL. `true` restricts to agents whose registration declares x402 support."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "note": {
       "description": "A declared skill is a claim, not a capability — each row already carries the verdict, so start with the rows that read safe and escalate the rest to GET /v1/verify/quick for the score and flags"
      },
      "agents": {
       "description": "agentId, identifier, name, endpoint, skills, domains, acceptsX402, payoutWallet, verdict (riskBand, blocklisted, confidence per payout wallet), checkedAt"
      },
      "matches": {
       "description": "total agents matching, across all pages"
      },
      "nextCursor": {
       "description": "offset for the next page, or null when exhausted"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/trustagent-agent-search-5aee3da3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from trust-agent.io](https://www.zero.xyz/host/trust-agent.io/llms.txt)