AI Passport

ServiceNow's signed runtime credential that defines and enforces what each AI agent or MCP server may do, with a kill switch.

ServiceNow · Security and safety tooling · security

Published in Feed

Overview

AI Passport, announced by ServiceNow on October 15, 2026 as part of its Super Intelligence Control Tower (formerly AI Control Tower), is a cryptographically signed credential recording an agent's identity, permitted actions, accessible systems and accountable owner. Passports are issued per agent, grounded in the enterprise CMDB, GRC policies and workflow approvals, and checked at runtime: out-of-scope agents can be redirected, restricted or terminated by a kill switch, with delegated permissions narrowing at each step and audit trails kept. It covers ServiceNow and third-party agents and MCP servers and is built on open specifications; NVIDIA is a design and launch partner, building enforcement on its Open Agent Safety Platform (OpenShell and Sentry). ServiceNow also announced shadow-AI detection with 400+ connectors and AI cost governance.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Signed per-agent credential: identity, permitted actions, reachable systems, accountable owner
  • Runtime enforcement: redirect, restrict or kill-switch termination, with audit trails
  • Covers third-party agents and MCP servers, built on open specifications
  • NVIDIA design and launch partner (OpenShell, Sentry on the Open Agent Safety Platform)
  • Shadow AI detection with 400+ out-of-box connectors
  • Cost governance by user, department and runtime

Use cases

  • Governing fleets of enterprise agents (LTM cites 1,500 agents with employee IDs and managers)
  • Limiting MCP server and agent permissions at runtime
  • AI governance, risk and security for financial institutions

Pricing

Not stated; one report expects release in Q4 2026.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
15 Oct 2026
Record updated
19 Oct 2026
Record last checked
19 Oct 2026

Explore the Feed

Other entries filed under security and safety tooling; inclusion does not imply equivalent features.

  • DefenseClaw Edge Connector

    Cisco's open-source DefenseClaw gains an Edge Connector that allows or blocks AI agent tool calls directly on IoT and robot hardware.

  • Lakera Guard 2.0

    Lakera's real-time guardrail API for LLM apps, updated with multi-agent protection and a new benchmark for detecting indirect prompt injection in tool outputs.

  • Fleming-1

    Sierra's model that listens to a live phone call and scores whether the caller is an AI agent rather than a human.

Browse the Feed