InterAI Risk Oracle MCP Server

Independent pre-execution decision layer for consequential agent actions. I’m Alejandro Bolognese, building InterAI through InterAI Labs as ongoing work on agent infrastructure, execution control, trust boundaries, and production systems. It is available as a remote MCP endpoint.

Teams that work with a2a, agent safety and autonomous agents and want a hosted endpoint instead of running a local process. The project is written in JavaScript.

VERIFIED ACTIVE

LAST COMMIT 2026-09-17 · ★ 1 · VERIFIED 2026-09-18

NOASSERTION · JavaScript servers · how we verify → /methodology

01 · Install InterAI Risk Oracle

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

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

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://api.interailabs.dev/mcp

transport: streamable-http

endpoint alive - responded to MCP initialize · probed 2026-09-17

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as remote - your agent's requests go to api.interailabs.dev

endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect

license no standard license detected - usage rights unclear; check the repo before commercial use

registry namespace io.github.InterAILabs is GitHub-verified and matches the repo owner

03 · Who maintains InterAI Risk Oracle

InterAI Risk Oracle is maintained by interailabs. It's the only MCP server we track from this author; the repo dates to Jun 2026.

04 · Facts

category
API integration - actively maintained as of 2026-09-18.
registry
io.github.InterAILabs/ai-risk-oracle (active, first published 2026-08-25 · 3 versions)

05 · InterAI Risk Oracle FAQ

What is InterAI Risk Oracle?

Independent pre-execution decision layer for consequential agent actions. I’m Alejandro Bolognese, building InterAI through InterAI Labs as ongoing work on agent infrastructure, execution control, trust boundaries, and production systems. It is available as a remote MCP endpoint.

Is InterAI Risk Oracle still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-17. We re-verify nightly.

How do I install InterAI Risk Oracle?

Run `claude mcp add interailabs-ai-risk-oracle --transport http https://api.interailabs.dev/mcp`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does InterAI Risk Oracle require authentication?

No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-09-17; you can connect without credentials.

06 · Alternatives to InterAI Risk Oracle