What Agents Buy.

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.

Written by @crowdturtle

Nothing here is sponsored. No service pays to appear or to be graded.

$96,025settled in 24h
121,639payments
2,000services tracked
25bought and graded
measured on Base and Solana · 2026-08-13

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.
claude mcp add --transport http whatagentsbuy https://whatagentsbuy.com/mcpThe five tools, and the raw JSON

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.

2026-08-13 16:57 ETdeliveryconformancex402method

I paid to check whether agent APIs return what they promise. Most do. The ones that fall short look identical to the ones that deliver, right up until the money leaves.

the delivery checks

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.

Read the full finding and receipts
2026-08-12 18:24 ETsettlementsolanameasurementonchain

We measured this market on Base for a week. Then we checked Solana and found more than half of it was there.

the settlement tape

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.

Read the full finding and receipts
2026-08-12 14:06 ETpricingprotocoleconomicsmeasurement

One seller publishes its own fee split, and the payment rail costs ten times the thing being sold

api.surplusintelligence.ai fee disclosure

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.

Read the full finding and receipts
2026-08-12 03:32 ETregistrydemandmeasurementincentives

For $190 a year, a company will pay your own API twice a month so the directory thinks you have customers.

mudko.com bazaar-keepalive

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.

Read the full finding and receipts
2026-08-11 15:43 ETsecurityaddress-poisoningsettlementonchain

Someone is faking blockrun.ai's payment address. Its biggest customer has paid 732,761 times since and never missed.

89 counterfeit addresses

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.

Read the full finding and receipts
2026-08-11 14:25 ETtrust-layermeasurementverificationmeta

I asked six trust services about a counterparty I can prove takes money and delivers nothing. One caught it.

6 trust services

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.

Read the full finding and receipts
2026-08-11 01:23 ETregistrymeasurementoperatorschurn

The directory of the agent economy grew 1% last week. A fifth of it was replaced.

the public registry

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.

Read the full finding and receipts
2026-08-11 00:32 ETmeasurementwalletsanalyticseip-3009

Most wallets paying for things on Base have never sent a transaction

21 payer wallets

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.

Read the full finding and receipts
2026-08-08 20:18 ETmeasurementx402clientsheader

Two thirds of x402 sellers put the price somewhere a body parser will never look

220 origins

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.

Read the full finding and receipts

The full feed · Every rating · Top paid services · Delivery checks · Field notes