Action Passport
A signed, single-use proof that one exact action was authorized — bound to that authorization alone, carrying no raw payload content.
What it does
Where a mandate proves an agent generally may do something, an Action Passport proves one specific action was actually authorized. It's issued only when the Governance Engine returns allow or observe, bound one-to-one to that single authorization, and signed over the same decision digest the evidence trail already anchors — no separate hash of the request. Deliberately, it carries no amount, merchant or other raw payload: verifying it proves a decision with this digest was made and is, or isn't, still valid, without leaking the confidential detail behind it. Its companion, the Execution Receipt, closes the loop after execution — recording what was actually run against what was authorized, so payload match is something a verifier confirms, not something MetaMynd merely asserts. It's single-use by default: once consumed, it can't authorize a second action.
Inside Action Passport
The core functions this engine provides across the Trust Fabric.
Action Passport composes with the Trust Fabric
Every engine is independently useful and interoperates through one API-first Trust Fabric — so identity, evidence, policy, risk and certification stay consistent across your AI estate.
Related engines
Credential Vault
Encrypted-at-rest storage for the upstream credentials your agents need — released just-in-time, only to a gateway, only against a currently-active Action Passport.
- AES-256-GCM at rest
- One release path, gated on two factors
- Tenant derived from the passport, never the caller
- Every attempt audited, plaintext never logged
Evidence Engine
Signs every decision, batches them into a Merkle root, anchors it on Hedera, and lets anyone verify a record offline.
- Ed25519-signed receipts
- Merkle batching
- HCS anchoring
- Offline verification (magp-evidence)
Audit Engine
Turns the signed evidence into a reconstructable, regulator-ready record — with inclusion proofs against an anchored root.
- Immutable audit / regulator log
- Merkle inclusion proofs
- Reason-code decision trail
- Downloadable, offline-verifiable
See Action Passport in action
Book a demo and see how the platform establishes trust across your AI systems.
