Machine-readable readiness

agentready.json turns a scan into a reusable readiness contract.

The AgentReady report is for humans. agentready.json is for tools, reviews, CI pipelines and future automation that need structured risk data.

Generate from OpenAPI Generate from MCP

What it contains

Source type: OpenAPI or MCP.
Generated timestamp.
Score and interpretation.
Severity counts.
Tool or endpoint findings.
Risk categories and recommendations.

Why it matters

It makes readiness portable.
It can support review workflows.
It can feed static simulations.
It can become the base for future CLI or CI checks.
It separates human report text from machine-readable findings.

Minimal example

{
  "agentready_version": "1.0",
  "source_type": "openapi",
  "summary": {
    "score": 62,
    "status": "Needs fixes",
    "risk_counts": {
      "critical": 2,
      "high": 4,
      "medium": 7,
      "low": 9
    }
  },
  "tools": [
    {
      "operation_id": "refundCustomer",
      "risk_level": "critical",
      "requires_human_confirmation": true
    }
  ]
}

Limit

TimeProofs AgentReady does not guarantee that an AI agent will never fail. It identifies structural risks that may cause AI agents to misuse APIs, tools or MCP servers.