
Argent decides with your own OPA server
If your team already runs Open Policy Agent, Argent can ask your server instead of its built-in one. Each agent request goes to your Rego policy first, and only an explicit allow lets it through.
What Argent does with your OPA server
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.
- Your Rego, your package. Argent posts each request to the decision document you name, such as
argent/authz. - Only an explicit allow. The request passes only when your policy returns
allow: true. An undefined decision document is a deny. - Every kind of agent traffic. Model calls, MCP tool calls, agent-to-agent calls and other gated requests from that tenant's agents all ask your server.
- Validated end to end. This connector is live-validated: a real allow, a real deny and an unreachable server that fails closed.
How it connects
Argent calls OPA's own REST decision API. Nothing is installed in your OPA server.
| Direction | Argent calls your engine once per request, at the endpoint you give |
| Call | POST <endpoint>/v1/data/<package> with {"input": ...} |
| Sign-in | None (a network-isolated server), a bearer token, or mutual TLS with a client certificate |
| 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 call is OPA's standard "Get a Document (with Input)" endpoint (OPA REST API). Argent reads result.allow from the reply and nothing else decides.
What your policy sees
Your engine gets the same facts on every request. None of them is a secret.
| Field | What it holds |
|---|---|
identity | The agent making the request, as Argent resolved it from its key |
scopes | The permissions that agent holds in Argent. May be empty; your policy decides what empty means |
tenant | The tenant the request belongs to |
request_class | The kind of traffic: llm, mcp, a2a, or unknown for anything else |
resource | The request path |
destination | The upstream host the request is bound for |
phase | headers: your engine decides before the request body is read |
model | Empty at the headers phase, because the body is not read yet |
No prompt, no request body, no key and no credential is ever sent to your engine. Because your engine decides before the 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 OPA server needs only a policy that answers `allow`.
- Write the decision. Add a Rego package to your OPA server that sets
allowfrom the input fields above. - Open Policy Engines. In Integrations, open Policy Engines and choose Open Policy Agent (Remote).
- Enter the server. The endpoint, such as
https://opa.internal:8181, and the package path, such asargent/authz. - Pick the sign-in. None, bearer or mutual TLS. For bearer or mutual TLS, give the reference to the stored credential; Argent refuses an authenticated mode with no credential.
- Optional. Pin your CA certificate for a self-signed server, and set a decision 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