IANA-AP
Intent Agent Native Authorization
for Agentic Profiles
Traditional authorization asks if a request is allowed. Agentic systems need to ask: does this request still belong to the plan you approved? IANA-AP binds every agent action to a plan the user approved with a passkey.
How It Works
The Four Phases of IANA-AP
It composes OAuth 2.0, OpenID AuthZEN, passkeys and MCP rather than replacing them.
Discover Required Authorization
The agent reads the service's Agentic Profile, a machine-readable definition that declares what authorization each tool requires.
Compute Authorization Intent
Using the discovered requirements and the user's prompt, the agent works out its planned operations and assembles them into a proposed intent.
Review and Approve
The full plan is surfaced natively inside the agent interface. The user approves with a single phishing-resistant Passkey gesture.
Runtime Enforcement
Every tool call is intercepted and checked against the approved intent before it runs. Anything outside the signed scope is blocked.
See It In Practice
Inside an Intent Agent Native Authorization Review
This is what the agent surfaces before it acts: the full plan, waiting on your Passkey. Here's what happens in each phase along the way.
Discover Required Authorization
Reads the Agentic Profile
Before doing anything, the agent reads the service's Agentic Profile via the MCP Server Card or tools/list response.
Only tools that opt in are pre-authorized
Each tool declares participation with an authorization mapping. Tools without one fall back to just-in-time approval instead.
Supported Agentic Profile Targets
Authorization Mapping in Agentic MCP Profile
Each tool opts in to IANA-AP with an x-authz-mapping that declares the authorization required to invoke it.
Compute Authorization Intent
Matches your prompt to what's needed
The agent maps your prompt against the mappings discovered in Phase 1 to work out exactly which actions, on which resources, are required.
Can plan, but can't act
This phase can run as a dedicated Intent Agent: a constrained component that computes the plan but has no ability to invoke tools.
Produces the agent_intent claim
Each planned tool call becomes one agent_intent entry, a structured claim the user will review and approve as a set in the next phase.
The SARC Model
Subject
Action
Resource
Context
Worked example, same plan shown in Phase 3:
Subject
alice, from the token
Action
tools/call
Resource
mcp-tool: disable_user
Context
the agent's identity
Review and Approve
One Passkey tap, every action covered
A single gesture approves the whole plan, not one prompt per action.
You can approve some, deny others
Approval isn't all-or-nothing. The Authorization Server can approve individual actions and deny the rest; the agent may only invoke tools whose entry was actually approved.
Execution Plan
3 actions awaiting your approval:
Awaiting Passkey approval to bind this plan
One gesture approves all 3 actions · nothing executes until then
Runtime Enforcement
Enforced exactly as approved
Once you tap, only these actions can run. Anything outside the plan is blocked at runtime.
No silent scope creep
Every call is checked against the signed plan again, every time. Approval never quietly expands.
The same SARC fields work with any PDP
Whether the decision is made remotely via AuthZEN or locally with Cedar or OPA, the enforcement point extracts identical Subject/Action/Resource/Context fields. Only the evaluation mechanism changes.
Policy Decision Point: Remote or Local
Remote PDP
OpenID AuthZEN
Local PDP
Cedar or OPA
Enforced at Every Stage of the Journey
Composable Authorization
Combine Authorization Layers for Your Security Posture
Activate the layers that match the risk of each operation, with the Authorization Server and policy engine you already run.
OAuth Security
Standard access control via OAuth and OpenID Connect. The baseline for every agent operation.
Intent Agent Native Authorization for Agentic Profiles
Pre-approve the full execution plan. Every action is cryptographically bound to the declared scope before the agent runs.
Just-In-Time Agent Native Authorization
Runtime step-up authorization for sensitive actions, backed by Passkeys and Human-in-the-Loop.
Why IANA-AP
Plan Before Execute
The agent cannot act until the user has approved its full plan.
Scope-Bound Proof
Every call is checked against the signed intent, down to the resource and its arguments.
Passkey-Backed Approval
One phishing-resistant gesture approves the whole plan.
Put every agent action under an approved plan
IANA-AP is powered by the Identity Access Plus (IA+) platform.