# agenttoll.dev MCP Safety Brief

> agenttoll.dev MCP Safety Brief is a paid API for AI agents from agenttoll.dev, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-16).

Generates a structured safety assessment for an MCP (Model Context Protocol) server or tool, including a risk score, risk level, approval requirements, and a recommended allowlist.

## Facts

- Endpoint: POST https://agenttoll.dev/paid/mcp/safety-brief
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agenttoll-dev-mcp-safety-brief-4f84111a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_adit5JYvIm2otWJE3YxlA

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 agenttoll-dev-mcp-safety-brief-4f84111a -d '<json body>'
```

Example prompt: Can you run a safety brief on this MCP server configuration I'm about to add to my agent — I need to know its risk score, whether human approval is required before it can run, and what the recommended allowlist looks like.

## When to prefer this

Choose this endpoint when you need a structured, scored safety assessment specifically for MCP servers or AI agent tools, especially in agent governance workflows where automated or human approval decisions depend on a numeric risk score and allowlist. Prefer it over generic security scanners when the context is AI agent tooling rather than traditional software vulnerabilities.

## Known failure modes

- Invalid or missing MCP server definition in request body — returns error or empty result
- Payment not processed via x402/Base USDC — endpoint returns 402 Payment Required
- Malformed JSON input — returns 400 Bad Request
- Score computation unavailable for unknown or undocumented tool configurations — may return low-confidence or null score

## How this service works

108+ receipt-backed x402 work products for AI agents. Clear prices, spend caps, buyer metadata, and structured results over Base USDC.

## Output

A JSON object containing the product name ('MCP Safety Brief'), a summary with a numeric safety score (0–100), a risk level (e.g. 'low', 'medium', 'high'), a boolean indicating whether human approval is required, and a recommended allowlist array of approved tools or endpoints.

## 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",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {
      "max_tools": {
       "type": "integer",
       "maximum": 25,
       "minimum": 1
      },
      "server_url": {
       "type": "string",
       "maxLength": 500
      },
      "openapi_url": {
       "type": "string",
       "maxLength": 500
      },
      "tool_schema": {
       "type": [
        "object",
        "string"
       ]
      },
      "openapi_json": {
       "type": [
        "object",
        "string"
       ]
      },
      "intended_task": {
       "type": "string",
       "maxLength": 240
      },
      "manifest_json": {
       "type": [
        "object",
        "string"
       ]
      },
      "sensitive_context": {
       "type": "boolean"
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "product": "MCP Safety Brief",
  "summary": {
   "score": 72,
   "risk_level": "medium",
   "approval_required": true
  },
  "recommended_allowlist": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttoll-dev-mcp-safety-brief-4f84111a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agenttoll.dev](https://www.zero.xyz/host/agenttoll.dev/llms.txt)