
Argent decides with Topaz
If you run Topaz, Argent can ask your authorizer about every AI agent request, in the open OpenID AuthZEN format. Topaz answers yes or no, and only a yes lets the request through.
What Argent does with Topaz
Keep the policy engine your team already runs. Argent asks it before any agent request goes out.
NIST's zero trust architecture, SP 800-207, puts it plainly: "Authentication and authorization (both subject and device) are discrete functions performed before a session to an enterprise resource is established." (NIST SP 800-207). Argent applies that to AI agents on every request: a policy engine decides, not the agent.
Most tenants use Argent's built-in OPA engine. A tenant that already writes its authorization rules in its own engine can route Argent's decision there instead, so one set of rules covers people, apps and AI agents.
Topaz, the open-source authorizer originally built by Aserto, is "an open-source, self-hosted, fine-grained access control service for modern cloud applications", with OPA as its decision engine (Topaz).
- An open standard on the wire. Argent sends an AuthZEN access evaluation: subject, resource, action and context.
- Only an explicit yes. The request passes only when Topaz returns
decision: true. A missing decision is a deny. - Short reasons only. A reason Topaz sends back is cut to a bounded length before Argent uses it.
- Validated end to end. This connector is live-validated: a real allow, a real deny and an unreachable authorizer that fails closed.
How it connects
Argent calls the AuthZEN evaluation endpoint on your Topaz authorizer.
| Direction | Argent calls your engine once per request, at the endpoint you give |
| Call | POST <endpoint>/access/v1/evaluation with subject, resource, action and context |
| Sign-in | None (a network-isolated authorizer), or an API key in a header you choose (default Authorization with the basic scheme) |
| Certificates | Certificate checks stay on. A self-signed engine is trusted by pinning its CA certificate, never by turning verification off |
| Network | Argent refuses private, loopback, link-local and cloud metadata addresses unless an operator has allowed that network range; the check runs when you save, with a reason |
| Credential | Stored as a reference in Argent's secret store, never in the connector settings, and dropped when the decision is done |
The OpenID Foundation announced the Authorization API 1.0 that defines this call as a Final Specification on January 12, 2026 (OpenID Foundation; specification). Argent uses the same AuthZEN definitions when it answers decisions itself, so the two cannot drift apart.
What your policy sees
AuthZEN subject, resource and action, filled from the request.
| AuthZEN field | What Argent sends |
|---|---|
subject | Type identity (or yours), id = the agent Argent identified; its scopes and tenant as properties |
resource | Type endpoint (or yours), id = the request path |
action | The request class, llm, mcp, a2a, or unknown for anything else, or one fixed name you set |
context | The request class, the phase (headers), the destination host and the tenant |
No prompt, request body, key or credential is ever sent to Topaz. Because Topaz decides before the request body is read, Argent's own model check still runs on the body afterwards, so a model nobody approved is refused as well.
What you configure
One connector, in the console. Your Topaz policy decides.
- Write the policy. Add a Topaz policy that answers for the subject and resource types above.
- Open Policy Engines. In Integrations, open Policy Engines and choose Aserto Topaz.
- Enter the authorizer. The endpoint, such as
https://topaz.internal:8383. Change the subject type, resource type or action name only if your policy expects others. - Pick the sign-in. None, or an API key with the reference to the stored key, plus its header and scheme if they differ from the defaults.
- Optional. Pin your CA certificate for a self-signed authorizer, and set a time limit up to 30 seconds.
Test the connection from the same page. Once the connector is active, every request from that tenant's agents is decided by your engine. Connecting an engine is an administrator's job: the Integrations page is gated by console role, like every console page.
Fail closed, every time
A policy engine Argent meant to ask but could not reach never allows anything.
- Timeout is a deny. Each decision has a time limit, 3 seconds unless you set another, and never more than 30 seconds. No answer in time means the request is refused.
- Errors are denies. A network error, a status other than success, or a reply Argent cannot read is a deny.
- No quiet fallback. Argent never falls back to its built-in engine when yours fails. Your engine may be stricter than the default, so substituting the default would be a way around your policy.
- Named reasons. A refusal from your engine is recorded as
pdp.external.deny, an engine that failed to answer aspdp.external.error, and one Argent could not build or look up aspdp.external.unavailable. The caller gets a 403; your engine's reply body and headers are never passed back to it. - Signed record. Every refusal goes on Argent's signed record with its reason, so an auditor can see which engine said no and why. See One-Click Audit Evidence.
- One tenant, one engine. The engine is chosen per tenant from the authenticated request, never from anything the caller sends. A tenant with no engine connected uses Argent's built-in OPA engine.
Where this fits
Pages that go deeper.
- Capabilities: Model Control, Agent Permissions, Watch Before You Enforce and all capabilities.
- Goals: model control and routing, agent identity and ownership, audit and accountability and all goals.
- Use cases: controlling agent tool access, securing AI coding agents and AI in regulated and air-gapped environments.
- Where it runs: air-gapped on-premises, private cloud or your public cloud VPC. Compare them on deployment options.
- Industries: Financial Services, Insurance, Healthcare, Public Sector and all industries.
- More integrations: every system Argent connects to, grouped by type, on the integrations page.
Want this running on your own use cases?
All downloads