Scope & reliance — 🔒 All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only. Embedded rates, thresholds, and regulatory citations are static reference values that may age — verify against current primary sources and your own data before relying on any output for commercial, legal, or compliance decisions. Deterministic logic · no inference · zero PII · CC BY 4.0.
Policy Mandate JSON Payload
🔒 All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Required Fields (UBC §3.1)
Valid mandate_type values
✓
Paste a Policy Mandate JSON payload
Validation results, compliance score, and deprecated field warnings will appear here.
Source — Valid AP2 Payload
The generator derives mcp_tool_definition.name from the tool_id field using verb_noun_context snake_case. It maps mandate_type to a recommended verb prefix. You can override the generated name.
Override Options
⊞
Paste a payload and generate
The MCP tool definition JSON block will appear here, ready to paste into your manifest.json.
AP2 Payload for Agent Simulation
What the simulator checks
  • → agent_instructions — present, non-empty array, each instruction is a non-empty string
  • → valid_until — present, future-dated, ISO 8601 format
  • → jurisdiction — present, non-empty array of ISO 3166-1 alpha-2 codes
  • → mandate_type — present, valid enum value
  • → audit_metadata — all three boolean flags present and true
  • → Guardrail coverage — checks for action words (block, escalate, alert, reject, report) in instructions
⚡
Paste a payload and simulate
The agent runtime simulation will step through each instruction and output a deployment readiness assessment.