# Agent Guard Capabilities Discovery

> Agent Guard Capabilities Discovery is a paid API for AI agents from agent-guard.annushka1190.workers.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-13).

Returns the list of available safety and trust tools offered by the Agent Guard service, including PII redaction, scam scanning, address validation, and more.

## Facts

- Endpoint: GET https://agent-guard.annushka1190.workers.dev/v1/capabilities
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-guard-capabilities-discovery-e588d860
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_TLdQfIAWjUA0LBxO_b9QO

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 agent-guard-capabilities-discovery-e588d860
```

Example prompt: Can you check what safety and trust tools are available on Agent Guard — like which PII masking, scam detection, and address validation endpoints I can call?

## When to prefer this

Use this endpoint at the start of any integration with Agent Guard to dynamically discover what safety tools are available rather than hardcoding endpoint paths. Ideal for agent bootstrapping, capability-based routing, and building adaptive safety pipelines that can automatically use newly added Agent Guard tools.

## Known failure modes

- Empty tools array if service is misconfigured or no capabilities are registered
- HTTP 402 if payment is missing or insufficient USDC balance
- HTTP 500 if the Cloudflare Worker encounters an internal error
- Malformed JSON response if the Worker script has a bug
- Stale capability list if new endpoints were added but not yet reflected

## How this service works

Safety and trust layer for AI agents: PII redaction, scam/phishing text scan, EVM/Solana address validation, IBAN checks, JSON repair, on-chain wallet heuristics, and x402 counterparty endpoint reputation checks. Free discovery endpoints included. Pay with USDC via x402 — no API keys.

## Output

A JSON object containing a 'tools' array listing all available Agent Guard capabilities, including their names, descriptions, pricing, and invocation details — effectively a service manifest for the Agent Guard safety platform.

## 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": {
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ]
    },
    "queryParams": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tools": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-guard-capabilities-discovery-e588d860/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-guard.annushka1190.workers.dev](https://www.zero.xyz/host/agent-guard.annushka1190.workers.dev/llms.txt)