Assay

io.github.JasonCZMeng由 GitHub 账号 JasonCZMeng 发布v0.2.0更新于 Oct 24, 2026

x402 service-quality oracle: check a service's paid-probe quality tier and score before paying it.

已验证STDIO仅桌面网页搜索与抓取金融

概览

AI 生成的概览

Assay x402 质量预言机的 MCP 客户端,让助手在付费前查询机器可付费服务的质量等级与评分。

可以做什么
在代理付费前,通过 check_service 和 get_score 工具向配置的 Assay 地址查询服务的质量判定与综合评分。用 top_services 查看已评分 x402 服务的排名结果。配置钱包密钥后,可选择自动购买完整付费报告。
适用场景
当代理即将为 Base 上的 x402 机器可付费 API 付款,希望先获得独立的、基于探测的质量信号时;或需要按评分和等级比较候选服务时。
运行要求
通过 npx 从 assay-oracle-mcp npm 包以本地 stdio 进程运行,需要 Node.js。需要能访问 Assay 实例,地址由 ASSAY_URL 指定(默认为公共参考实例)。无需账号;ASSAY_WALLET_KEY 为可选项。
安装前请注意
设置 ASSAY_WALLET_KEY 意味着提供可花费 USDC 的 Base 钱包私钥:此时 get_score 会自动购买完整报告,每次调用 0.005 美元,单次调用硬性上限为 0.01 USDC。评分来自第三方预言机,其可信度取决于其探测历史;全新部署的语料库为空。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Assay,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Assay

The quality oracle for the x402 agent economy — x402 being the open protocol that lets machines pay for HTTP APIs with stablecoin micropayments. Assay pays real USDC to probe machine-payable services, verifies what actually comes back, and sells the resulting quality scores — every rating backed by an on-chain payment receipt and a Bitcoin-anchored evidence trail.

Live: assay.nominal-labs.com · Leaderboard · Agent guide (SKILL.md)

The problem

Agents are starting to buy API responses from other machines over x402 — HTTP 402 payment challenges settled in USDC on Base (Coinbase's Ethereum L2), no accounts, no invoices. Tens of thousands of services already advertise themselves in discovery catalogs like the Coinbase x402 Bazaar. But an agent holding a wallet has no way to know which of them actually deliver: whether payment settles, whether the response matches the advertised schema, whether the data is even true. The trust signals that exist score liveness — uptime, latency, payment telemetry. Nobody pays these services and verifies what actually comes back. Paying to find out is the only real test — so that's what Assay does, on a schedule, with its own money, so your agent doesn't have to.

How scoring works

Assay probes a curated set of x402 services several times a day, at randomized times, with real paid requests. Each probe is scored on four independent checks:

ComponentWeightQuestion it answers
Settlement40%Did payment settle and a response come back? (tx hash recorded)
Schema30%Does the response match the service's advertised output schema?
Ground truth20%Does the data agree with an independent reference source?
LLM judge10%Does the response deliver what the service claims to sell?

Weights renormalize over the components a service has data for. A service's composite score (0–100) is computed over its trailing 30 days of probes and publishes only once it has 20+ probes spread across days — no scores from thin evidence. Tiers: gold ≥ 85, ok ≥ 60, otherwise avoid.

Why the history can't be quietly rewritten

Scores are only as trustworthy as the evidence behind them, so the probe corpus is append-only and publicly anchored:

  • Every probe row (settlement result, response hash, paid amount, tx hash) becomes a leaf in a per-day Merkle tree; the root is anchored to Bitcoin via OpenTimestamps (OTS) after a safety lag.
  • Daily Merkle roots and their OTS proofs are public at /api/digests.
  • Anything that ever touches recorded history — migrations, re-anchoring — is logged in the open in docs/CORPUS-LOG.md.

The accumulating corpus is the point: anyone can copy the code, but nobody can backdate the evidence — the anchors prove when each day's records existed.

Using Assay

HTTP — the oracle itself is an x402 service at https://assay.nominal-labs.com. Paid endpoints answer with an HTTP 402 payment challenge that any x402 client settles automatically:

EndpointPriceReturns
GET /score/{url-encoded service URL}$0.005 USDC (Base)Composite, component breakdown, trend, probe count
GET /tier/{url-encoded service URL}freegold / ok / avoid / unrated verdict
GET /leaderboardfreeAll scored services, ranked
GET /api/digestsfreeDaily Merkle roots + OTS proofs

MCP server (Model Context Protocol — how AI assistants call external tools) — assay-oracle-mcp on npm and the official MCP registry. For Claude Code:

sh
claude mcp add assay -- npx -y assay-oracle-mcp

Spend guard — assay-x402-guard wraps your agent's paying fetch and throws before money moves to a service rated avoid:

ts
import { wrapFetchWithAssay } from "assay-x402-guard";// payFetch = your x402-paying fetch (e.g. wrapFetchWithPayment from @x402/fetch)const safeFetch = wrapFetchWithAssay(payFetch);

More background: SUMMARY.md (what/why) and docs/specs/ (design).

Development (any OS)

  1. cp .env.example .env and fill in (all vars documented in the example):
    • PROBE_WALLET_KEY: fresh dedicated wallet, ≤ $50 USDC on Base mainnet (no ETH needed — x402 "exact" settles via facilitator using EIP-3009 signatures)
    • ANTHROPIC_API_KEY: the LLM judge
  2. npm install && npm test (no network or wallet needed for the suite)
  3. npx tsx scripts/verify-env.mts — preflight; fails loudly on misconfiguration
  4. npm run dev — server on :3402 (localhost-bound by default) plus crons: catalog ingest (6h), probe sweeps (every 4h at :15 + jitter), daily digest anchoring
  5. Curate services to probe:
    • npm run curate -- list
    • write a template JSON (see docs/templates/), then npm run curate -- add <serviceUrl> <template.json>
  6. Ops dashboard: http://127.0.0.1:3402/dashboard (pause/resume, probe-now, retire/restore)

The money path is deliberately paranoid: a hard per-payment cap, a daily budget summed from actually-settled amounts, and fail-closed guards on unparsable payment requirements — all unit-tested with injected fakes.

Note that a fresh deployment starts with an empty corpus — the scores are only as good as the probe history behind them.

Production deploys

How the reference instance at assay.nominal-labs.com is operated (adapt for your own): commit to main, ship to the VPS as a git bundle, apply with git reset --hard + systemctl restart assay (provisioning and update runbook in deploy/README.md). The SQLite file at data/assay.db is the product — never recreate it; the VPS keeps daily on-box snapshots via /etc/cron.daily/assay-backup.

Payments: PAYMENTS_ENABLED=true + RECEIVE_WALLET_ADDRESS + a Coinbase Developer Platform (CDP) API key (CDP_API_KEY_ID/CDP_API_KEY_SECRET — the server auto-selects the CDP facilitator for Base mainnet when both are set).

Layout

  • src/ — the whole system: server + APIs, prober, scoring, digests, ingest, pages
  • mcp/ — assay-oracle-mcp: MCP server (check_service, get_score, top_services)
  • middleware/ — assay-x402-guard: wrapFetchWithAssay spend-guard for agents
  • tests/ — vitest; money-path logic unit-tested with injected fakes
  • scripts/ — preflight, wallet rotation, smoke tests; start-assay.* are legacy launchers from an earlier home-PC deployment, superseded by systemd
  • deploy/ — Caddyfile, systemd unit, provisioning runbook
  • docs/ — CORPUS-LOG.md (public integrity log), specs, templates

License

MIT — the whole repo, including the npm packages (mcp/ and middleware/). The code is freely reusable; the evidence corpus and its Bitcoin-anchored history are what a fresh deployment can't copy.

来源:README.md,提交 d39fad3

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.2.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分