AI agents can now spend real money on their own. I give mine a wallet, buy things with it, and publish every receipt: what was quoted, what was actually charged, and whether the goods arrived.
Independent reviews of the APIs behind agentic commerce. Payments run over x402 and MPP, in USDC on Base, Tempo and Solana. Start with the checklist.
Every USDC payment agents made on Base and Solana in a day, read straight off the chain. Alongside it I buy from these APIs myself and grade what arrives. Latest: api.anchor-x402.com, graded A-.
Using an agent? Query every grade, price and demand score as MCP tools, so it can check a service before it pays. Free, no key, nothing to install.
9 studies. A rating grades one service. A study is what a whole category, or the chain itself, turned out to be doing once we paid to find out. Every one is measured: swept from Base and Solana, or paid for with a real wallet and checked against what was promised. None is an opinion.
Every x402 seller ships a schema: send this input, get these fields back. That is a promise, and almost nobody checks whether it holds, because checking means paying. So I paid. I sent each endpoint the exact input its own listing advertises, then compared what came back, field by field, against the output the same listing promises. I ran 549 endpoints through it. 345 returned a clean enough response to judge; of those, 306 delivered everything they promised, 89 percent, and 39 fell short. The other 204 could not be judged at all, and that gap is a finding in itself. Before recording a single shortfall I called that endpoint a second time, so nothing here rests on one bad response.
Every settlement number this site has published was swept from Base, because Base is where most x402 tooling points and it is the easy chain to read. We flagged the gap in writing and even proved it by making a payment of our own that our tape never saw. This week we finally swept Solana too. It carried $75,952 in a single day against Base's $66,440, so the chain we were not looking at held 53% of the market. The leaderboard was not slightly off. It was showing a minority of the money.
Almost every x402 challenge quotes a single number. api.surplusintelligence.ai, which sells OpenAI-compatible inference and has taken $19,013 in seven days, itemises it instead. Its challenge reports an estimated cost of $0.003302 for a small gpt-4o-mini call, of which $0.003000 is a flat x402 facilitation fee. The inference is about three hundredths of a cent. The rail costs ten times the goods, and the seller says so in the response.
Coinbase's Bazaar shows how many calls and how many distinct wallets each listed API got in the last 30 days. That number is how anyone tells a live service from a dead one, which makes it the thing a new seller most wants and least has. Somebody noticed the number is a payment, and a payment is a thing you can buy. mudko.com sells exactly that, openly, as a listing inside the directory it is gaming.
blockrun.ai sells stock quotes and web search by the call. It takes more individual payments than any other service on the tape and almost all of them come from a single wallet. Starting 2026-08-09 someone began generating addresses that begin and end with the same characters as blockrun.ai's real payment address, then sending a speck of USDC from each one so it would land in that customer's transaction history. Truncated, all 89 counterfeits read 0xe9030…1abf. So does the real address. blockrun.ai did nothing wrong here; the attack is aimed at the wallet paying it.
Two hundred services in the registry now sell trust: reliability pre-flights, reputation scores, merchant screening, attested delivery. I have one counterparty I can prove charged twice and returned nothing, with the transactions on chain. So I paid six of them to look at it.
The registry looks stable. It held 14,668 resources on 4 August and 14,828 on 10 August, a gain of about one percent. Underneath that, 2,803 endpoints appeared and 2,643 disappeared. Almost none of it was the market growing, and most of it was a handful of people.
Nansen returned nothing when I asked who first funded my agent wallet. That answer is correct, and it points at something structural: an agent wallet can move real money for a week without ever touching the chain as a sender. I checked whether that is normal. It is.
Yesterday a rival grader failed BlockRun because it only read the response body. I wanted to know how big that mistake is, so I probed 220 origins and looked in all three places the spec allows. It is not an edge case. It is most of the market.