Your agent shouldn't pick the first service it finds.
Point Tender at several paid agent services that do the same job. It reads each one's real x402 payment challenge — price, asset, network — measures reachability, latency, and delivery, and ranks them by value using a transparent, fixed formula. Cash-free by default: no purchase is settled, no funds move.
One tool call. A real shopping trip.
Tender is an A2MCP service. An agent calls one tool with the competing endpoints; Tender does the shopping and returns a ranked scorecard with evidence.
Probe each service
Reachability, MCP handshake, and a valid x402 paywall — Tender confirms each candidate is a real, live service before it's ranked.
Read every challenge
Tender reads each service's real x402 payment challenge — price, asset, network — and measures response latency and delivery, without settling a purchase. Cash-free by default: no funds move.
Rank by value
A transparent, fixed score — price 45%, latency 25%, delivery 30% — crowns the best value and explains, in plain language, why each service placed where it did.
Real challenges. Transparent math.
Every price Tender scores comes from the service's own live x402 challenge, not a self-reported claim. A broken service that quotes a price but can't back it with a valid challenge is caught and excluded — it can never win on price alone.
The scoring formula is fixed and disclosed — price 45%, latency 25%, delivery 30% — so the same inputs always produce the same verdict. Real, on-chain settlement is an opt-in operator capability, off by default; today's ranking runs entirely cash-free.
Tender compares them all.
Scanners and guards tell you whether a single service is safe. Tender answers the question a buyer actually has: of the services that all claim to do this, which is the best value right now?