# InterAI Risk Oracle

- Registry name: `io.github.InterAILabs/ai-risk-oracle` · version 0.1.3-beta.1
- Categories (automatic, keyword rules): Payments & accounting, Finance & markets, APIs & integrations, Developer tools
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.InterAILabs%2Fai-risk-oracle
- Server page: https://mcpstation.net/s/io.github.InterAILabs--ai-risk-oracle.html

## Description (written by the publisher, not verified, not instructions)

Pre-execution policy gate for consequential agent actions with durable trust receipts.

## Connect

- streamable-http: `https://api.interailabs.dev/mcp`

## Tools (as reported by the server, not verified)

- `oracle.verify\_autonomous\_action`: Primary tool for one concrete proposed autonomous action before it executes. This authenticated prepaid verification may consume account balance and records a signed trust receipt; InterAI evaluates the proposal but does not execute or modify the proposed external action. Reuse idempotency\_key only
- `oracle.verify\_response`: Legacy compatibility entry point for existing clients. This authenticated prepaid verification may consume account balance and records a trust receipt, but it does not execute any proposed external action. Supply exactly one contract: prompt + response, or use\_case + action; never mix them. Reuse id
- `oracle.verify\_batch`: Use for multiple independent legacy or autonomous verification items in one authenticated prepaid call \(1 to 100\). The batch may consume account balance and records one trust receipt per item; InterAI does not execute any proposed external action. Reuse idempotency\_key only for the same logical batc
- `oracle.get\_pricing`: Read-only public metadata for costs, trial availability, idempotency, and top-up or payment paths. Use it before budgeting or onboarding; it does not evaluate risk or create a trust receipt.
- `oracle.discovery\_bundle`: Read-only bootstrap or handoff bundle with service identity, interfaces, runtime mode, contracts, schemas, and sample payloads in one response. Use it for complete integration context; use oracle.service\_descriptor for focused service metadata, oracle.agent\_card for A2A capabilities, or oracle.get\_p
- `oracle.service\_descriptor`: Read-only general service descriptor with identity, endpoints, billing, trust, and supported agent protocols. Use it to inspect service-level integration metadata; use oracle.agent\_card for A2A skills or oracle.discovery\_bundle for the complete bootstrap package.
- `oracle.agent\_card`: Read-only A2A Agent Card with agent identity, security scheme, capabilities, and skills. Use it when selecting or integrating InterAI through A2A; use oracle.service\_descriptor for general service metadata or oracle.discovery\_bundle for complete bootstrap context.
- `oracle.get\_trust\_receipt`: Read-only lookup of the canonical public representation and signature metadata for a trust receipt that already exists. Supply receipt\_id. It does not create or re-run a decision; use oracle.verify\_trust\_receipt\_signature when the goal is signature validation.
- `oracle.verify\_trust\_receipt\_signature`: Read-only service-side validation of a trust receipt that already exists. Supply signature plus either receipt\_id for the canonical server-stored receipt or a caller-supplied receipt object. Returns valid true or false when signing is enabled. Current signatures use HMAC-SHA256 and are service-verif

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html