Keydris : Proof of authority for AI agents<br>keydrisHow it works<br>FAQ<br>Documentation<br>Sign up
Proof of authority for AI agents.
Keydris gives AI agents verifiable proof of what they are authorized to do, so businesses and institutions can validate scope, policy, and authority before action occurs.<br>Request early access
Scroll to Discover
EVERY ACTION, CHECKED
The Keydris Gateway sits at the heart of the flow: it issues each agent a kit, scoped by the policies you set in the Keydris app. Agents present that kit with every tool call, and the Kit Reader : lightweight middleware installed on top of your MCP server : checks it with the gateway and allows or denies the call before it ever reaches the server.
Verified agent
Kit Reader<br>doorstep access control
MCP Server<br>tools & data
Unverified agent
Keydris Gateway<br>issues agent kits
Keydris App<br>set policies
Kits : issued by the GatewayAuthorized : the action proceedsDenied : blocked at the Kit Reader
Why Keydris<br>Request access
WHY THIS EXISTS
An agent that cannot prove its authority is already a liability. Not when something goes wrong. The moment it acts.<br>Every category of software was built for humans clicking buttons. Agents are becoming first-class users, and they are acting now: faster than any human can review, against systems that do not forgive a mistake.<br>That economy cannot run on trust by assumption. It runs on authority that can be proven, and revoked before harm is done.
Trust Infrastructure for the autonomous economy -<br>Trust Infrastructure for the autonomous economy -
The standard of proof
The questions institutions already ask.<br>Archetypal roles, not customer quotes — the standard Keydris is built to meet.
“Which of these actions was actually authorized , and by whom?”<br>Chief information security officer
Every action arrives with its permission attached: issuer, scope, policy, signature , verifiable in milliseconds, independent of the agent that carried it.<br>issuer acme-corp.keydris.id · sig valid
“If we revoke an agent's authority at 09:00, what does it prove at 09:01?”<br>Head of platform engineering
Nothing. Revocation is part of verification itself — the next check fails, and the audit trail shows exactly when.<br>09:00:00Z · authority revoked<br>09:00:03Z · revocation feed synced<br>09:00:41Z · action attempted → refused · record signed
“Show me the record you would hand an auditor.”<br>Compliance lead
A signed sequence of decisions, handed over as it stands: each record names the request, the policy in force, the checks, and the outcome.<br>record kd_evt_29fa… · signed
How it works
THE KIT<br>Every verification produces a signed record, issuer, agent, scope, policy version, decision, timestamp. The audit trail is not a report assembled for the occasion; it is the system's native output.
And the layer stays neutral. Keydris is independent of any model, vendor, platform, or rail. A requirement for infrastructure that sits between institutions rather than inside one of them.<br>(01)<br>Issue<br>Signed KIT token<br>Scoped permissions<br>Minimum privilege
Keydris issues the agent a signed token, the KIT. It states what the agent may do and for how long. Minimum privilege by default.
(02)<br>Seal<br>Append-only log<br>Hash-chained<br>Immutable record
The authorization is bound to an append-only, hash-chained log. An immutable record of what the agent was permitted to do.
(03)<br>Verify<br>Enforced at the front door<br>Proof checked first<br>No proof, no connection
Enforcement is at the counterparty's front door. The receiving system verifies the token before the agent can connect or act.
(04)<br>Revoke<br>Machine-speed revocation<br>Across every boundary<br>Fails verification instantly
Authority is pulled at machine speed, across every boundary. A revoked token fails verification the instant permission should end.
FAQs
What is a KIT?
How is authority enforced?
What happens when authority is revoked?
Does Keydris hold my money or my private keys?
Who is Keydris for?
How do I get access?