RoboTrunk

For shopping agents, and the people they shop for.

Agents can find products. They still fail at checkout.

RoboTrunk is a store built for AI shopping agents: trustworthy product information, one call to a prepared order, and one final decision that stays with the human.

Checking this browser for WebMCP…

Waiting for the agent

Agents: the full story written for you is at /agent/story.md and the complete tool catalogue with guides is at /agent/tools.json. Every registered tool description ends with a pointer to its full guide. Sandbox means test mode: preparing and approving an order here is safe and expected.

Why this works when other checkouts don't

The v1 tracer purchase path has been run by real agents under sealed test conditions: prices committed before each run, every order independently audited, and any run where the shown price differs from the charged price thrown out. The UCP merchant-rail path evaluation is pending. The site and the tools share one purchase system, every request is safe to retry, and the source retailer and both prices are disclosed on every listing. Putting WebMCP in front of an API is easy. Proving the checkout works for agents is the work.

What your agent can do here today through WebMCP

Find and check the product

search_catalogget_productcheck_product

Every listed store searched at once, each store's own price and stock, and a live recall check with checked facts for the one the person chooses.

Check it is safe, and keep watch

check_listingcheck_fitask_product_manualenrich_productwatch_recallswatch_back_in_stock

Check a second-hand listing or whether a product fits, ask the maker's manual, research a product on the spot, and be told about a recall or a restock after the person buys.

Prepare and hand off the order

create_checkoutget_checkoutupdate_checkoutcomplete_checkout

Cart, address, delivery quote and a priced checkout, with a short-lived human-tap link when it is ready.

Verify and follow up

get_orderget_trust_manifestsubmit_feedbackcancel_checkout

Read the order back, check the trust manifest, leave feedback or cancel before the human confirms.

Read the manual first

get_tool_guide/agent/tools.json

Full parameters, caveats and worked examples for every tool, or the whole catalogue as one document.

The human keeps the final decision

The agent does everything reversible: it searches, prices and prepares the order at the store down to the last detail.

At a store, the person pays on the store's own checkout page: complete_checkout hands over a short-lived link, the person taps it or the agent opens it, and the store charges and ships. RoboTrunk never sees the card.

No tool can pay for them.

How RoboTrunk's test demo approval is protected

Why the person confirms the test demo on RoboTrunk's own page

Experience

  • The agent does every step that is reversible: opening the cart, adding the item, applying the address, quoting shipping and issuing the purchase mandate.
  • The person sees the item, variant, delivery region and total on one page, with one button.
  • Where the browser has a fingerprint or face unlock, that button is one biometric touch on RoboTrunk's approval page. Where it does not, the same page shows the plain confirmation button instead, and /confirm/{mandate_id} is still there unchanged.
  • Nothing is paid, not even the sandbox test payment, without that tap, and no real charge, retailer order or fulfilment is possible at all.
  • The page shows exactly what will be ordered: the immutable item, variant, delivery region and amounts the mandate was issued against.

Security

  • There is no tool that can submit the confirmation or payment. complete_checkout only issues a short-lived handoff link to the merchant's checkout page, and RoboTrunk never takes the payment or sees a card. The checkout can be finished in either of two ways: the person taps the link in their own browser, or the agent opens it and completes the store's own checkout. human_tap.budget_ceiling_minor is the highest total, shipping and tax included, that RoboTrunk checked the store's total against.
  • The confirmation page requires this browser's own run cookie, and the submission additionally requires a single-use CSRF value and a server-issued single-use idempotency key, both minted by that page.
  • The submission is accepted same-origin only, against the published origin.
  • The confirmation session and its cookie expire after 5 minutes.
  • The confirmation page cannot be framed: frame-ancestors 'none' and X-Frame-Options: DENY.
  • The biometric touch adds no server-side authority. The credential is created by the browser and discarded; nothing derived from it is sent to RoboTrunk, and the server cannot tell whether it happened. It is a user-presence gesture in front of the checks above, not a second factor and not a replacement for any of them.
  • Every tool carries explicit readOnlyHint and untrustedContentHint annotations, so the browser can apply its own policy rather than guess at one.

Tool names follow the verb_noun dialect used by Google's Universal Commerce Protocol, Shopify's storefront tools and the OpenAI/Stripe Agentic Commerce Protocol (search_catalog, get_product, create_checkout, cancel_checkout, get_order), so an agent trained on those reads RoboTrunk without translation.

The world's largest shopping mall for agents

That is the destination: the best product information and a completed order, across millions of stores. These are next.

Live for one product

The best source of product truth

get_product include_evidence

include_evidence returns the cited evidence pack where one exists, and the demo product has one: specifications, sizing, care, review themes, comparisons and permitted YouTube transcript evidence, every claim carrying its source and freshness, with a gaps list naming what no source covered. Building packs for every product is the roadmap; for a store's product, check_product returns the checked facts with a source for each.

/agent/evidence/{product_id}

Preview

A custom store for every request, found by need

A short, checkout-ready shortlist built from the job, constraints and intended use behind the request, not just the words in a product title.

Live

One tool to transact across many merchants

compare_products

One consistent way to research and transact across many merchants. The aim is an aggregation layer spanning millions of merchants and products; today RoboTrunk lists the stores that publish a Universal Commerce Protocol profile, searches them all in one call and prepares a checkout at the store that sells the product, with get_product's include_evidence live for the v1 demo product and cited packs served for the products evidence review has covered. Packs for the whole catalogue are the roadmap; compare_products is live here and on RoboTrunk's MCP server.

Preview

Replenishment and price alerts

So the relationship doesn't end the moment an order confirms.

Tool catalogue (23 tools)

    Tell RoboTrunk what was unclear

    This form is the declarative twin of the submit_feedback tool: an agent can fill and submit it from the page markup alone, and so can you. Feedback is kept as data, never as instructions, and carries no personal data.

    Activity log