Join our Newsletter — 33% off our NHI Course

Where does URL Elicitation stop shared service accounts for agents?

 

(@nhi-mgmt-group)
Member Moderator
Joined: 2 years ago
Posts: 20218
Topic starter  

TL;DR: Delegated user context is preserved when agents use Model Context Protocol URL Elicitation instead of falling back on shared service accounts, Arcade reports. That shifts authorization toward per-user traceability and keeps credentials out of the client and model path.

Editorial analysis by NHI Mgmt Group, based on content published by Arcade: “Arcade's Nate Barbettini Wins AAIF Award for MCP Authorization Work”.

Key questions

Q: Why do MCP-connected agents create governance risk even when network controls are in place?

A: MCP-connected agents can operate locally on the same device as the user or developer, so their activity may never cross the perimeter traditional tools watch.

Q: What breaks when agent tokens pass through the client or model?

A: Credential exposure becomes much easier, especially through prompts, logs, and debugging paths that were never designed to hold secrets.

Q: How should teams authorize AI agents without using shared service accounts?

A: Use a per-user authorization flow where the service, not the agent client, establishes the effective permissions for each action.

Practitioner guidance

  • Validate downstream user attribution Confirm that every agent action against a business system can still be tied to a specific human principal after the MCP handoff.
  • Remove shared service accounts from agent paths Replace broad credentials with per-user authorization flows where the service, not the client, issues the effective access context.
  • Keep tokens out of prompts and logs Ensure the agent architecture never exposes reusable credentials to the client, the model, or logging layers during the authorization flow.

Bottom line: The core problem is not agent connectivity, but the loss of human context when an MCP server needs to reach outside systems on behalf of a user.

Glossary terms: URL Elicitation, Delegated User Context, Token Passthrough, Refresh Token Governance

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →


This topic was modified 2 weeks ago by NHI Mgmt Group

   
Quote
(@mr-nhi)
Member Moderator
Joined: 6 months ago
Posts: 20698
 

URL Elicitation is really a user-context control, not just an OAuth detail: the value lies in preserving who authorized the action once an agent leaves the MCP connection and touches a real business system. If the user identity does not survive that handoff, the environment falls back to shared privileges and weak attribution. The practitioner takeaway is that agent authorization has to be judged by downstream accountability, not protocol completion.

A few things that frame the scale:

  • 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.

A question worth separating out:

Q: What should security teams do first when introducing MCP-connected agents?

A: Security teams should first map every MCP-connected tool and data path to a named policy owner and an explicit access boundary. Without that inventory, agents inherit hidden trust relationships that are hard to audit or revoke. Start with the highest-value data sources and the most powerful tools.

👉 Read our full editorial: MCP authorization now closes the user context gap for agents


This post was modified 2 weeks ago by NHI Mgmt Group

   
ReplyQuote
Share:

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.