InterAI Risk Oracle MCP Server

by interailabs Your server? Claim it

answering

InterAI Risk Oracle is answering right now. Last checked 6 min ago. It exposes 9 tools. Last commit 29 Sep 2026.

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

Uptime history 54 days of history · worst day 67%

54 days agonow

98.9%

Uptime 24h

182 of 184 checks

Tools

read from the server

530 ms

Response time

average over 24h

Stars

last commit 29 Sep 2026

What changed 29

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 7 September 2026. No other catalogue keeps this.

16 Sep a tool changed version

11 Sep 3 tools changed the parameters they ask for oracle.verify_autonomous_action, oracle.verify_batch, oracle.verify_response

10 Sep 5 tool descriptions were rewritten8 times that day oracle.get_trust_receipt, oracle.verify_autonomous_action, oracle.verify_batch and 2 more

10 Sep 2 tools changed the parameters they ask for oracle.get_trust_receipt, oracle.verify_trust_receipt_signature

9 Sep 3 tools changed the parameters they ask for oracle.verify_autonomous_action, oracle.verify_batch, oracle.verify_response

8 Sep 9 tool descriptions were rewritten oracle.agent_card, oracle.discovery_bundle, oracle.get_pricing and 6 more

7 Sep 3 tools changed the parameters they ask for oracle.verify_autonomous_action, oracle.verify_batch, oracle.verify_response

and 3 more, back to 7 September 2026

InterAI Risk Oracle missed 2 checks this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ai-risk-oracle": {
      "url": "https://ai-risk-oracle.fly.dev/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.ai-risk-oracle]
url = "https://ai-risk-oracle.fly.dev/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "ai-risk-oracle": {
      "url": "https://ai-risk-oracle.fly.dev/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "ai-risk-oracle": {
      "url": "https://ai-risk-oracle.fly.dev/mcp"
    }
  }
}

This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.

Available tools 9

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

oracle

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.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_pricing for costs.

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.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.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.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 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.

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 batch retry. For one proposed action, use oracle.verify_autonomous_action instead.

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 idempotency_key only for the same logical retry. For new action preflight use oracle.verify_autonomous_action; use oracle.verify_batch for multiple items.

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-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.

Endpoints

URL	Transport	State	Latency	Checked
https://ai-risk-oracle.fly.dev/mcp	streamable-http	answering	653 ms	6 min ago
https://api.interailabs.dev/mcp	streamable-http	answering	620 ms	6 min ago

Alternatives to InterAI Risk Oracle

same job, measured the same way

ActionDock

by actiondock

Supervised API-write gateway for AI agents with policy, human approval and execution receipts.

8 tools answering

ONCE — Exactly-Once Reliability for AI Agent Actions

by gsterlingpress

Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.

2 tools answering

Covalt Execution Gateway

by covaltpay

Trusted execution infrastructure for AI agents. Proposal-only protocol with human consent.

answering

Emilia Protocol

by emiliaprotocol

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

71 installs/wk local only

TookEffect

by tookeffect

Independent effect verification and signed receipts for consequential AI agent actions.

answering

Decionis

by decionis

Authorize consequential AI agent actions before execution

86 installs/wk answering

Sato Kit

by satohub

Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.

109 installs/wk local only

Agent Gate

by forgeorbital

Local mandate gate and proof trail for AI agents that take consequential actions.

51 installs/wk local only

InterAI Risk Oracle — questions

Answers built from our own checks of this server.

What can InterAI Risk Oracle do?

It exposes 9 tools, read directly from the server on our last check. Among them: oracle.agent_card, oracle.discovery_bundle, oracle.get_pricing, oracle.get_trust_receipt, oracle.service_descriptor, oracle.verify_autonomous_action and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is InterAI Risk Oracle working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 182 of 184 checks got a reply (98.9%), average response time 530 ms. The bar chart above shows every period we have measured.

How do I connect InterAI Risk Oracle?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does InterAI Risk Oracle need an API key?

No. InterAI Risk Oracle completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is InterAI Risk Oracle?

It answers our handshake in 530 ms on average, which is faster than 21% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is InterAI Risk Oracle open source?

We cannot say either way: written in JavaScript and 1 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.