{"uid":"cap_AdK28sidAq0yy5olRA3LA","slug":"humanmirror-safe-preflight-a10f13f9","name":"HumanMirror Safe Preflight","description":"","url":"https://humanmirror.fr/api/x402/safe-preflight/","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["input"],"properties":{"input":{"description":"JSON-serializable input for this deterministic outcome."},"options":{"type":"object","description":"Optional tool-specific options."},"criteria":{"type":"object","description":"Optional deterministic acceptance criteria."}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}},"additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_k1KDDpoN7orKPhWH3MuKW","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Pre-flight validates a proposed AI agent tool call or command against a declared operational risk limit before allowing execution.","exampleAgentPrompt":"Before you execute that DELETE operation on the customer records endpoint, run a preflight safety check on it — the body is {\"input\": {\"table\": \"customers\", \"where\": \"status=inactive\"}} and I want to make sure the operational risk stays within acceptable limits.","exampleUseCases":[{"title":"Gate destructive database command","prompt":"Before running that DROP TABLE migration script, preflight it for me — the body is {\"input\": {\"action\": \"drop_table\", \"table\": \"orders_archive\"}} — I need to confirm the risk is within bounds before we proceed."},{"title":"Validate autonomous agent tool call","prompt":"My AI agent is about to call an external payment API with {\"input\": {\"amount\": 5000, \"currency\": \"USD\", \"recipient\": \"vendor-42\"}} — can you preflight that tool call to verify it's safe before it executes?"},{"title":"Safety-check bulk update operation","prompt":"I have a bulk PATCH request my agent wants to send — body is {\"input\": {\"update_all\": true, \"field\": \"status\", \"value\": \"archived\"}} — run a preflight check on it and tell me whether it passes the risk threshold."}],"resultDescription":"Returns a preflight verdict indicating whether the proposed tool call or command is safe to execute, including whether operational risk stays within the declared limit and whether any specified acceptance criteria are met.","failureModes":["Missing required 'input' field returns validation error","Invalid HTTP method (non-POST/PUT/PATCH) rejected by schema","Malformed body type enum causes request rejection","Input not JSON-serializable results in parsing error","Risk threshold exceeded returns a failed preflight verdict","Network timeout on evaluation for complex inputs"],"whenToPreferThis":"Choose this endpoint when you need a fast, deterministic safety gate for AI agent tool calls or automated commands before execution — especially when the action is irreversible, affects external systems, or must stay within a declared operational risk limit. Prefer this over generic logging or monitoring when you need a synchronous go/no-go decision point in your agent pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-19T12:33:43.871Z","isFirstParty":false}