io.github.InterAILabs/ai-risk-oracle
repo:https://github.com/interailabs/ai-risk-oracle
Policy gate and signed trust receipts for autonomous agent actions.
- transport:
- remote
- credential class:
- self-provisionable
Owner verification
Not yet verified. Verifying proves you control this server and is free, permanently — it never changes a published score.
Start verification →Tools
- oracle.agent_cardshallow
Return the A2A Agent Card published at the well-known location.
- oracle.discovery_bundleshallow
Return the single-fetch discovery bundle with interfaces, runtime mode, schemas, and sample payloads.
- oracle.get_pricingshallow
Return public pricing, trial, idempotency and top-up metadata for self-serve integration.
- oracle.get_trust_receiptshallow
Resolve the canonical public trust receipt representation by receipt ID.
- oracle.service_descriptorshallow
Return the agent-oriented AI service descriptor with billing, trust, A2A and endpoint metadata.
- oracle.verify_autonomous_actionshallow
Bill one prepaid autonomous_execution verification and return allow, review_required, or block with policy signals and a signed trust receipt.
- oracle.verify_batchshallow
Bill one prepaid batch verification against the authenticated account and return trust receipts for up to 100 items.
- oracle.verify_responseshallow
Legacy compatibility alias for prompt/response verification and existing MCP clients. Prefer oracle.verify_autonomous_action for new integrations.
- oracle.verify_trust_receipt_signatureshallow
Verify a signed trust receipt payload when signing is enabled on the server.
Embed this server’s score
Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.
[](https://vouch.tools/servers/f8f32e4f-e6fc-43b3-a10d-e2b72ca166eb)