Decide what an assistant may do and when it needs approval. In a pilot agreed with your team, Trusteed applies the rules your platform supports and lets you consult the available evidence for the operation.
Before you see what is ready · During you apply your rules · After you consult the available evidence.
checkoutScope: Trusteed is not a payment processor and not merchant of record: the charge is made on the merchant's own payment account, with their credentials. Nor does it replace your own records or legal obligations. See full limits
Start by checking whether your products are easy to understand. In a pilot, choose which purchases need review. If a receipt is issued for an action, you can see what was recorded.
Find out what to fix so an assistant can understand your products and buying terms. The free audit returns an Agent Score for readiness, separate from the operational Trust Score.
Agree with your team on which operations to test, which limits to apply and when to ask for approval. Each pilot covers the actions and rules your platform supports.
When the pilot scope supports it, a signed TrustReceipt helps verify what was recorded and which evidence is still missing.
Choose a scenario to see when a purchase needs confirmation and when it is blocked. These are simulated examples with fixed decisions: they do not place orders or query your store.
{ "tool": "complete_checkout", "amount": 6400, "agent_status": "verified"}The operation may continue. The user confirms before checkout.
Rafi, our AI avatar, explains how the arrival of shopping agents is changing the rules of online commerce, and what it means for your store.
An assistant prepares an order above your spending limit. Agree on which actions need confirmation before testing delegated purchases. The simulation on this page shows a EUR 420 order that requires approval, without making a real purchase.
A technical identifier does not always explain who operates the agent or what its purpose is.
Verify the context before exposing a sensitive action.How we evaluate contextA request that is valid on its own can lock inventory, drain promotions or split orders.
Agree on limits and approval points for the pilot actions.How we apply limits and human reviewPrice, stock, seller or terms may no longer match what was approved.
Check price and stock again in the flows that support it.See the scope of checkout controlTo review a purchase, you need to know what was requested, what was decided and which evidence is missing.
When a receipt is issued, consult the record and the missing evidence.See the sample TrustReceiptTrustReceipt keeps the available context of identity, consent, policies and operation. Its signature lets you check who issued the record and whether it changed afterwards; on its own it does not prove that the underlying fact happened.
It is not a complete lifecycle chain nor a universal legal guarantee. Evidentiary weight depends on the jurisdiction, the process and the concrete evidence available.
tr_01JY7E4M8X...A92FIndividual signed record, issued in production. That every checkout generates one, or any volume, cannot be claimed: issuance was enabled and producing at the last check (2026-10-01), and the live counters are published at /api/v1/health, and a count does not say what fraction of covered actions produced a receipt. The lifecycle graph remains planned.
Score for merchant: demo-store (demo store, synthetic data)
The public v4.1 surface already takes part in ranking and eligibility. It is not a customer review, and it is not a score for Trusteed: it is this merchant's.
There is limited history available. Interpret this score with caution; it does not guarantee future purchases.
The public methodology is 4.1.0. Each response declares the overall and breakdown engines; when engines.mixed is true, the v2 breakdown does not explain the v4.1 overall.
How the Trust Score is measured ↗No. Trusteed is designed as a layer on top of existing systems.
Yes. Identity answers who is requesting the action; on its own it does not explain whether the sequence is economically abusive.
No. The current corpus contains individual receipts. The causal lifecycle graph is still behind flags that are off: it is not available today.
No. It strengthens traceability and evidence readiness. Evidentiary weight depends on the case, the recipient, the process and the jurisdiction.
Control and Evidence are offered through guided pilots. Assurance helps evaluate the starting point.
MCP endpoint
POST https://trusteed.xyz/{storeSlug}/mcp/discoveryJSON-RPC 2.0: replace {storeSlug} with the slug published in merchant-index.json. Discovery needs no credential.
Discover the tools
tools/listRead the actual tool set on the selected endpoint; tools depend on each store.
Cart and checkout: /{storeSlug}/mcp/checkout. Real merchants need OAuth; demo-store uses a sandbox key and simulated payments.
If the bucket returns bucket_not_enabled_for_store, use the legacy /{storeSlug}/mcp alias. Check real-payment availability in the registry; a checkout endpoint does not prove settlement.