> ## Content Index
> Fetch the complete content index at: https://www.agentsecbrief.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# What is an authorization boundary?
- URL: https://www.agentsecbrief.com/what-is-an-authorization-boundary/
- Published: 2026-11-20T17:20:39.000Z
- Updated: 2026-11-20T17:20:39.000Z
- Description: An authorization boundary is the point where a system actually checks whether an action is allowed and refuses it if not, such as an IAM role, a database permission or a sandbox.
- Author: Angela Milash
- Tags: Agent Identity & Auth, MCP, Glossary

## What is an authorization boundary?

An authorization boundary is the point where a system actually checks whether an action is allowed and refuses it if not, such as an IAM role, a database permission or a sandbox.

### Why it matters

AI agents are often limited by instructions in their prompt or by an "approve" button in the app. Neither is a check the target system enforces, so a confused or manipulated agent can still do anything its credentials allow. Knowing where the real boundary sits tells you what an agent can actually do.

### Example

On 13 November 2026 Microsoft added write tools to its Azure Resource Manager MCP server, which runs every call with the signed-in user's Azure rights. Microsoft's own governance page says a prompt such as "don't change resources" "isn't an authorization boundary" and that approving a tool call in the client grants no permission ([Microsoft Learn](https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/azure-resource-manager-mcp-governance?ref=agentsecbrief.com)).

### How to defend against it

- List every tool an agent can call and write down which system enforces its limit (RBAC, database role, network policy, sandbox).
- Give agents their own identity with the narrowest role that does the job, instead of the user's full rights.
- Test the limit: have the agent attempt an out-of-scope action and confirm the target system refuses it.
- Log actions under the agent's identity so you can see what it did (see the [AgentSec checklist](https://www.agentsecbrief.com/checklist/)).

### Related terms

Delegated authority, excessive agency, confused deputy, least privilege

### Sources

- [Microsoft Learn: ARM MCP server governance](https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/azure-resource-manager-mcp-governance?ref=agentsecbrief.com)
- [Microsoft Learn: ARM MCP server tools](https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/azure-resource-manager-mcp-tools?ref=agentsecbrief.com)

*From AgentSec Brief, the daily brief on securing agentic AI. Subscribe free at https://www.agentsecbrief.com*