AI agents buy on behalf of your customers. Without verifiable identity, without a mandate, without an audit trail. MT Shopping changes that — for end users, merchants, and platforms alike.
Sarah told her agent: up to 150 euros, buy on your own; above that, ask me. Last week it bought headphones for 340 euros. Did she set it up wrong? She has no way to tell — and neither does the platform.
Hundreds of orders a day from shopping agents. Some legitimate, some bots gaming inventory. They all look the same on the wire, and he can't tell them apart.
Agent traffic went from 8% to 34% in twelve months. No record of who these agents are, who owns them, or what they are allowed to do. Chargebacks rise. Regulators ask who is liable.
A W3C-based, immutable identifier, anchored on Base L2 and independently verifiable by every party.
The Agent Authorization Envelope defines what the agent may do: spending limits (autonomous / approval-required / blocked), categories (allowed / blocked), time windows, and jurisdictions. Signed by the owner, verifiable offline in <2ms.
Every action becomes an Interaction Proof Record, Merkle-anchored on Base L2. A Trust Score (0–100) gives merchants and platforms a signal to act on.
REST API — works with any commerce stack.
Convenience SDK: npm install @moltrust/sdk
Pricing is the same across every MolTrust vertical — start free, then priced per active agent (Base and Scale). See full pricing → · per-call rates → /pricing#usage
Payment: USDC on Base (via x402).
MT Shopping verifies shopping-agent authorization and records each action. It moves no money — payment stays on your existing rails. It runs alongside any agent framework and any commerce stack, and it stores only interaction metadata, never purchase content. It is platform-agnostic by design.
All endpoints are free. No signup required. Start verifying agent purchases today.
// BUILD WITH MOLTRUST
Add agent verification to your API in one line.