InterAI Risk Oracle

by InterAILabs · remote · no sign-in to list tools · v0.1.3-beta.1 · published by GitHub user InterAILabs

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

Changes · 3

Compare Registry entry

9 tools: 3 change things and 6 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things3Claude Code: ask: see these tools
Only reads6Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http ai-risk-oracle https://api.interailabs.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

9 tools

Changes things 3Creates or changes something that can be changed back.Claude Code: ask

oracle.verify_autonomous_actionPrimary tool for one concrete proposed autonomous action before it executes.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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 when retrying the same logical request to avoid duplicate billing. Returns allow, review_required, or block with policy signals. Use oracle.verify_batch for multiple independent items and oracle.verify_response only for legacy prompt/response compatibility.
Annotations the server declares
- title: Verify Autonomous Action
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
oracle.verify_batchUse for multiple independent legacy or autonomous verification items in one authenticated prepaid call (1 to 100).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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 batch retry. For one proposed action, use oracle.verify_autonomous_action instead.
Annotations the server declares
- title: Verify Batch
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
oracle.verify_responseLegacy compatibility entry point for existing clients.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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 idempotency_key only for the same logical retry. For new action preflight use oracle.verify_autonomous_action; use oracle.verify_batch for multiple items.
Annotations the server declares
- title: Verify Response (Legacy)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false

Only reads 6Looks things up and changes nothing.Claude Code: allow

oracle.agent_cardRead-only A2A Agent Card with agent identity, security scheme, capabilities, and skills.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: A2A Agent Card
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
oracle.discovery_bundleRead-only bootstrap or handoff bundle with service identity, interfaces, runtime mode, contracts, schemas, and sample payloads in one response.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it
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_pricing for costs.
Annotations the server declares
- title: Discovery Bundle
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
oracle.get_pricingRead-only public metadata for costs, trial availability, idempotency, and top-up or payment paths.No findings
Why it is in this group
- The name "oracle.get_pricing" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Get Pricing
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
oracle.get_trust_receiptRead-only lookup of the canonical public representation and signature metadata for a trust receipt that already exists.No findings
Why it is in this group
- The name "oracle.get_trust_receipt" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Get Trust Receipt
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
oracle.service_descriptorRead-only general service descriptor with identity, endpoints, billing, trust, and supported agent protocols.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Service Descriptor
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
oracle.verify_trust_receipt_signatureRead-only service-side validation of a trust receipt that already exists.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it
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-verifiable by InterAI, not independent offline public-key proofs. It does not evaluate risk or create a receipt; use oracle.get_trust_receipt to retrieve receipt metadata.
Annotations the server declares
- title: Verify Trust Receipt Signature
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.3-beta.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http ai-risk-oracle https://api.interailabs.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__ai-risk-oracle__oracle_get_pricing",
      "mcp__ai-risk-oracle__oracle_discovery_bundle",
      "mcp__ai-risk-oracle__oracle_service_descriptor",
      "mcp__ai-risk-oracle__oracle_agent_card",
      "mcp__ai-risk-oracle__oracle_get_trust_receipt",
      "mcp__ai-risk-oracle__oracle_verify_trust_receipt_signature"
    ],
    "ask": [
      "mcp__ai-risk-oracle__oracle_verify_autonomous_action",
      "mcp__ai-risk-oracle__oracle_verify_response",
      "mcp__ai-risk-oracle__oracle_verify_batch"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as ai-risk-oracle. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.InterAILabs/ai-risk-oracle/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:16 UTC.

For agents: Markdown · JSON · report this listing