HiveKey
Home/ Enforcement/ Least-privilege scoping
Enforcement · Core enforcement

Least-privilege scoping.

An agent gets exactly the tools its job needs — and not one more.

in the path

// policy

role: support-agent → scope [mail.send, crm.read]

vault_get → reveal API key deny
Why it matters

A raw key is all-or-nothing, and a confused or hijacked agent's blast radius is exactly the set of things it can reach. Least privilege keeps that set as small as the job allows.

How it works

Grant an agent the precise set of actions its job calls for, packaged as a reusable role. Anything you don't grant never shows up in its tool manifest — it can't call or even discover it.

01

Intercept

The agent attempts an action. HiveKey catches it in the path — nothing reaches the tool yet.

02

Evaluate

Scope is defined once as a role and applied across the fleet — read-only by default, with every write a deliberate grant rather than the starting point.

03

Enforce & log

The verdict is enforced — allow, block, or route for approval — and written to the audit trail, attributable to the agent's owner.

Agent

attempts an action

HiveKey

scope · guard · log

Tool / MCP

only allowed actions

What you get

Built for security and platform teams.

The smallest possible blast radius per agent

One role, defined once and applied across the fleet

Ungranted tools are invisible to the agent, not just blocked

Part of Scope

Least-privilege scoping is one expression of Scope.

Every capability rides the same spine — Scope what an agent can do, Guard each action in the path, Log all of it on one trail.

Explore Scope

Enforce every action your agents take.

Scope, guard, and log every action — and enforce it in the path, before anything happens.