vet402-check MCP server
io.github.kzmttkc/vet402-check·v0.2.0Before your agent pays an x402 API, check if vet402 bought it with its own money and what came back.
0 stars496 downloads/wk
Reviews
Write oneNobody has reviewed vet402-check yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
vet402-check tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
check_before_payingGive the URL you are about to pay (and, if you have them, the chain and the payTo from the 402). Returns what vet402's public record holds about that seller: how many purchases vet402 made with its own money on Solana, Tempo, Base or Algorand, how many settled, how many came back with an answer, the newest purchase with its tx, the failures counted against the seller and the ones that are not, the
diagnose_failed_paymentGive the transaction of a payment you made (a Solana signature or a Base tx hash), the URL you paid and, if you have it, the HTTP status the seller answered. Reads the payment from public RPC (settled or not, payTo, amount, asset, time) and puts it next to vet402's own purchases from the same seller on the same chain within 24 hours. Returns fault: seller_side, facilitator_side, buyer_side or unde
verify_recordGive a record id (obs_YYYY-MM-DD_NNNNNN) or the https URL of a published record. Checks, without taking vet402's word for it: the bytes are the ones the records index lists, the signer is a vet402 observation key, the EIP-712 signature, that the verdict follows from the recorded checks, the Merkle proof to the day's root, the payment on chain over public RPC, and the day's root in a Solana memo se
Public scan report
scanner v0.1.10 · 2026-10-09 · same rubric, same numbers if you re-run it
- Code scan53 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How vet402-check compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 4,460 AI and agents servers
- Tools
- 3
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 496
- more than 86% of 1,538 AI and agents servers with a package
What its tools let an agent do: 3 read
Install vet402-check in Claude Code, Cursor or VS Code
Runs npx -y @vet402/check on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add vet402-check -- npx -y @vet402/check
What the publisher says
From the vet402-check repository's README, as published. We do not edit it. Read it on GitHub
vet402-delivery
Before an AI agent pays for an API, vet402 has already bought it with its own money and shows what came back, with the payment on chain.
On Solana, Tempo and Base since 2026-09-28 (UTC). The current counts (purchases, sellers, payments settled, answers that came back, and payments that settled with nothing usable back) are at the top of the site's first page and in site/rank.json: the groups[] entry with id main, its totals (the top-level totals include Algorand).
- See the results: https://kzmttkc.github.io/vet402-delivery/ (Solana, Tempo and Base first; Algorand on its own page)
- Check one record yourself, no account and no payment: from a clone of this repository, npx tsx scripts/verify-receipt.ts https://kzmttkc.github.io/vet402-delivery/records/obs2026-09-28000001.json
- Look a seller up before paying, in one line (CLI, MCP server, x402 fetch hook): see Try it in 60 seconds and packages/check/
- Use it in an agent, between "search" and "pay": skills/vet402-check/
Who it is for:
- People who build agents that pay: look a seller up before your agent pays it.
- Sellers: see whether a real outside payment to your API settled and what your API answered. It costs you nothing, and there is nothing to sign up for.
"Came back with an answer" means the payment settled and the seller answered 2xx with a non-empty body (for the Tempo census purchases, whose runner kept no body: 2xx; the Tempo re-purchases are tested for an empty body). On Solana, Tempo and Base the runner checked each payment on chain before calling it settled. vet402 did not check that the answer is what the listing promised; whether its keys matched what the seller declared is a separate column.
How vet402 pays for this: Grades come only from vet402's own purchases. vet402 also sells paid checks (paid in USDC on Algorand or Base); a paid check is a separate report and never moves a grade.
Where Solana comes in: vet402 pays Solana sellers in USDC on Solana, and writes the Merkle root of each day's signed delivery records into one Solana memo, so a record of that day cannot be added or dropped later without the root changing.
This README carries no counts: the daily publish commits only data/ and site/, so counts written here would fall behind. The site is rebuilt from data/ on every push to main, so it shows the purchases whose results have been committed to data/, not ones still waiting to be copied there.
This repository is the multi-chain part of vet402. It buys the sellers it can on Solana (from the PayAI, CDP Bazaar and Pay.sh catalogs) and Tempo (from Tempo's Mercator directory), and on Base the sellers registered in ERC-8004 (8 purchases from 8 sellers on 2026-09-28, each bought once). Rebuy plan from UTC day 2026-09-29, with no end date: every day, twice on Solana and once on Tempo, one purchase per payTo per slot per UTC day among the Solana and Tempo sellers whose earlier payment settled (which ones: the rows in data/remeasure/), within a cap of 70 USDC per calendar month on Solana and 30 USDC.e on Tempo. It keeps every result with its payment, and grades sellers by what was actually delivered, not by how popular a listing is.
Try it in 60 seconds
Node 22 or newer. Nothing to sign up for, no key, no payment: the check reads rank.json, the signed records and the records index, and nothing else.
npx -y @vet402/check https://api.xona-agent.com/token/pumpfun-trendingIt prints what vet402's record holds about that seller: purchases tried, settled and answered, the failures counted against the seller and the ones that are not, the grade (measuring while there are too few purchases), the newest purchase with its tx, and the signed records. For a seller vet402 never bought from, it prints "vet402 has no record of this seller". The first run installs from GitHub (about 30 seconds on an empty npm cache).
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
vet402-check: common questions
- Is vet402-check MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the vet402-check safety report
- How do I install vet402-check?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does vet402-check need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is vet402-check maintained?
- The last commit was 26 days ago (2026-10-09). The latest release is v0.2.0.
- What can I use instead of vet402-check?
- Servers from other publishers that do the same job: Decionis MCP server, Kiln MCP server and Vibe Check MCP server.
- How does vet402-check compare with other AI and agents MCP servers?
- safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to vet402-check
Same job from other publishers: the closest match first, then the best rated.
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- KilnSpawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.not reviewedEstablishedB
- Vibe CheckMetacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safetynot reviewedEstablishedB
- agentburnLocal profiler: which usage window took you out, and where your agent's money goesnot reviewedEstablishedA
- paper-preflightChecks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.not reviewedEstablishedA