Notifications
Clear all
Topic starter
04/06/2026 3:00 pm
TL;DR: AI clients are rapidly being embedded into emergency management and government workflows, while MCP-linked agents often arrive with long-lived, broadly scoped credentials that create a binder problem across tools and environments, according to Strata Identity. The governance issue is not the agent itself but the absence of centralized delegated access, auditability, and short-lived assignment-based permissions.
NHIMG editorial — based on content published by Strata Identity: AI clients, MCP, and the emergency operations model for agentic identity
By the numbers:
- The initial release in v2026.04.2 ships Session Passthrough.
Questions worth separating out
Q: How should security teams govern AI agents that need access to multiple enterprise systems?
A: Security teams should broker access centrally and issue short-lived, task-scoped credentials for each tool and upstream system.
Q: Why do long-lived credentials create a bigger risk for AI agents than for traditional automation?
A: AI agents can choose tools and sequence actions dynamically, so long-lived credentials become durable authority across many unpredictable requests.
Q: What breaks when agents are given personal access tokens and service account keys directly?
A: What breaks is separation of duty and revocation discipline.
Practitioner guidance
- Replace bundled secrets with delegated assignment tokens Map every credential an agent can see today, then remove any reusable secret that is not tied to a single task, upstream, and expiry.
- Enforce per-tool authorization at runtime Require policy evaluation on every tool call, not just at agent start-up, and make the decision include user context, task scope, and destination system.
- Separate check-in from execution authority Give the agent a single entry point for identity, then broker all downstream access through a central coordinator that can log, scope, and revoke each request independently.
What's in the full article
Strata Identity's full analysis covers the operational detail this post intentionally leaves for the source:
- Architecture walkthrough of the Maverics AI Identity Gateway and how its brokered access flows differ from static secret storage.
- Step-by-step explanation of Session Passthrough, Federated Exchange, and Brokered Exchange for downstream systems.
- Deployment references for OAuth, RFC 8693 token exchange, OPA policy evaluation, and delegation tokens in agent workflows.
- Practical examples of how the EOC metaphor maps to real identity operations in internal and third-party systems.
👉 Read Strata Identity's analysis of AI agent delegated access and the EOC model →
AI agents in emergency response: is your access model ready?
Explore further
04/06/2026 3:12 pm
Agentic access breaks the assumption that identity should hold authority before the work begins: The binder model is built on the premise that a runtime can safely retain reusable access until someone reviews it later. That premise fails when the actor is an AI agent because tool use is distributed across many calls, many systems, and many short-lived decisions. The implication is not simply that credentials need tighter scopes, but that governance must stop treating standing authority as a stable state.
A few things that frame the scale:
- 97% of NHIs carry excessive privileges, increasing unauthorised access and broadening the attack surface, according to Ultimate Guide to NHIs.
- 92% of organisations expose NHIs to third parties, raising supply chain risk across delegated access paths, according to Ultimate Guide to NHIs.
A question worth separating out:
Q: What frameworks help teams control AI agent access and delegated identity?
A: OWASP NHI and NIST Zero Trust Architecture are the most relevant starting points because they both assume access must be continuously governed and tightly scoped. For agentic workflows, teams should extend those controls to per-call authorization, short-lived delegation, and clear audit trails across every upstream system the agent can reach.
👉 Read our full editorial: AI agent identity in emergency operations needs delegated access control
