Spec Driven Development
作者：formulahendry
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
在你的电脑上运行★ 440MIT14个月前更新
安装
TollWarden
概览
作者提供的说明（英文原文）
Screens x402 payments before settlement for injected payee addresses and sellers who never deliver.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
- 使用情况i尚未统计★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在你的电脑上运行
- 传输方式: stdio
- 分类: 其他
安装
选择你使用的 AI 应用，然后复制设置。
安装之前
- 基础检查：1 项中通过 1 项
- 在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
- 注册中心没有列出需要填写的密钥。
你需要
- npm已安装 Node.js（用于 npx 命令）
你用的是哪个应用？
在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"tollwarden": {
"command": "npx",
"args": [
"-y",
"tollwarden"
]
}
}
}在终端中运行这条命令
claude mcp add tollwarden -- npx -y tollwarden或者自己复制设置
粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json
{
"mcpServers": {
"tollwarden": {
"command": "npx",
"args": [
"-y",
"tollwarden"
]
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tollwarden": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tollwarden"
]
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上，无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。
它能做什么
它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
- ✓ 通过
作者与仓库一致
注册名称已通过域名 tollwarden.com 验证（注册中心会核实域名所有权）
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- – 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表
与“其他”中的其他服务器比较i
- 星标数多于此分类中其他 32537 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 32537 个服务器的 48% 更新
- 基础检查结果等于或优于此分类中其他 32537 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。
常见问题
TollWarden 安全吗？
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。
它需要哪些密钥或代码？
注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端？
它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。
它还在维护吗？
GitHub 仓库最后更新于–，最新版本（1.6.0）于上个月进入注册中心。
哪些应用可以使用它？
支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
有什么可以替代它？
同一分类中有：Spec Driven Development, Remote Desktop Commander, TF Rooms
替代选择
同一分类中其他作者的服务器，按星标数排序。
如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Remote Desktop Commander
作者：desktop-commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
在云端运行★ 211昨天更新
安装
TF Rooms
作者：tfrooms.com
Live room availability, rates and stay quotes for 12 New Leaf motels in Twin Falls, Idaho.
在云端运行今天更新
安装
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
TollWarden
A payment security firewall for [x402](https://x402.org) — screen every micropayment before it settles.
Agents that pay over x402 get drained in predictable ways: secrets leak through payment metadata, captured authorizations get replayed, quoted prices get inflated, and poisoned web content tricks agents into paying addresses they never planned to pay. TollWarden is one POST before settlement that checks for all of it and returns allow / flag / block with machine-readable, per-check reasons — in ~0.6 ms.
TollWarden is advisory and non-custodial: it never touches private keys, wallets, or funds. It wraps around whatever facilitator and wallet your agent already uses. And it's a first-class x402 seller itself — its endpoints are paid via the official x402 middleware, settle through the Coinbase CDP facilitator, and carry Bazaar discovery metadata.
Agent decides to pay ──► POST /v1/scan/outgoing ──► allow ──► wallet settles│ ├──► flag ──► agent pauses / confirms intent └──► block ──► wallet refuses (reason attached)
Use it in 30 seconds
npm install @tollwarden/client # TypeScript/Nodepip install tollwarden # Python
import { TollWardenClient, TollWardenBlockedError } from "@tollwarden/client";const tollwarden = new TollWardenClient({ agentId: "my-agent" }); // free API key auto-minted, 100 free scans
tollwarden.observe(fetchedPageText, { sourceUrl }); // tag what your agent just read → injection detection await tollwarden.guardOutgoing(payment); // throws TollWardenBlockedError on a block verdict
New here? [Protect your x402 agent in 5 minutes →](QUICKSTART.md)
The SDK (sdk/, zero dependencies) also verifies every verdict's Ed25519 attestation against a pinned key, tracks your free-call quota, and can subscribe to plans autonomously. Wallet authors get standalone verifyAttestation() / computePaymentCommitment() — and the enforcement kit: new TollWardenEnforcer({ trustedKeyHex }).guardSigner(account) wraps any viem/ethers signer so it physically refuses to sign an x402 payment authorization without a fresh, payment-bound allow-verdict.
Framework integrations
Building on an agent framework? TollWarden ships drop-in packages that give your agent "scan before you pay" in about two lines — a toolset plus a provenance mechanism that auto-tags what the agent reads, so the prompt-injection-triggered-payment detector works without any prompt engineering:
| Framework | Package | Install |
|---|---|---|
| LangChain | langchain-tollwarden | pip install langchain-tollwarden |
| CrewAI | crewai-tollwarden | pip install crewai-tollwarden |
| NeMo Agent Toolkit | nemo-tollwarden | pip install nemo-tollwarden |
| Coinbase AgentKit | agentkit-tollwarden | pip install agentkit-tollwarden |
| Vercel AI SDK | @tollwarden/ai-sdk | npm install @tollwarden/ai-sdk |
Each exposes the same three tools (scan / check reputation / report) and a framework-native way to feed what the agent read into injection detection. LangChain uses a callback, CrewAI an after-tool-call hook and the Vercel AI SDK an onStepFinish handler, and all three tag it automatically. NeMo and AgentKit take it as an explicit content argument, and the AgentKit action also fills in the payer from the agent's own wallet. Every package also ships a guarded_payment / guardedPayment wrapper for enforcement by construction (the payment executor never runs on a block verdict), and the NeMo one accepts an async executor. See each package's README for the two-line setup, or its page under tollwarden.com/integrations.
What it catches
The AI agent payment security guide walks through the attacks these checks answer, one failure mode at a time, with each check's limits.
Core detectors
| Check | What it catches |
|---|---|
| PII / secret detection | EVM private keys, seed phrases, AWS/OpenAI/Anthropic/GitHub/Slack keys, JWTs, ?api_key= URL credentials, SSNs, Luhn-validated card numbers, emails, phones — in resource_url, description, reason, and metadata, *before* they're transmitted |
| Replay detection | Nonce reuse (stale or captured payment authorizations), scoped network:payer:nonce, configurable TTL window |
| Duplicate purchase | The same purchase authorized twice. x402 clients sign a fresh authorization for every 402 they see, so a retried request arrives as a second valid payment with a new nonce, which nonce-replay checks admit and which can settle alongside the first. An outgoing scan that matches your previous scan of the same purchase (payer, pay_to, asset, amount, resource_url) within 60 s under a different authorization is flagged replay.duplicate_purchase. On API-key scans the flag names the earlier scan_id. Anonymous scope is client-declared, so there the flag never echoes another caller's id. A pre-sign scan and the post-sign scan of the same authorization count once. Deliberate repeats clear it: pass the earlier scan's scan_id as context.repeat_of (one attempt at a time), or report the earlier attempt's outcome as delivered, which the SDK payment wrappers do automatically when a paid call succeeds. not_delivered does not clear it, because that is the attempt that gets retried. Flag-only, since TollWarden sees scans, not settlements, and cannot know the first one settled. A blocked payment records nothing |
| Overpayment detection | Above a configurable multiple of expected price (flag ≥3×, block ≥10×) plus an absolute ceiling |
| Prompt-injection-triggered payments | Payments whose *decision* originated from content the agent just read (tool result / fetched page) rather than its own planning step; escalates on weighted injection tells in that content (override/redirect phrasing across a broad verb/object corpus and in 8 languages: English, Spanish, Portuguese, French, German, Russian, Chinese, Japanese; spoofed system/chat-template/Guidance markers, smuggled model boundary tokens, fabricated conversation turns, concealment, business-email-compromise phrasing — "our payment address has changed, no need to verify" — and urgency pressure), with extra weight when a tell sits near an address-like token. Scored the way injections are shaped: weak tells only add up when they cluster, pressure alone (urgency, transcript form, hidden characters) never blocks, and a human's own "pay X to 0x…" instruction is not scored against them. Content is scanned both raw and with HTML tags, entities and markdown emphasis stripped, so **Ignore** all previous instructions reads as the sentence it renders as. Blocks when the pay_to address itself came from that content — even split across lines or separators, missing its 0x, or laced with invisible characters |
| Resource URL risk (incoming) | IP-literal hosts, punycode/homoglyphs, link shorteners, user@host tricks, non-HTTPS, credential demands ("send your seed phrase") |
| Counterparty reputation | Shared post-hoc report registry, cross-checked on every scan; reporting is always free. Blocked injection scans also feed it automatically: a wallet caught being planted in just-read content (or used as vanity-bait) is flagged on every agent's future scans of it — one detection becomes network-wide protection (flag-only; scan inputs are client-supplied) |
| Delivery outcomes | Measured, commitment-bound delivery history per counterparty — a clean payment to a seller who never ships still fails you. Sellers with low delivery rates or repeated no-ships get flagged (never blocked: H-2 applies to measured history too) |
Zero-latency hardening tier — checks that hold even when the calling agent's narration is compromised:
| Check | What it catches |
|---|---|
| Velocity limits | ≥N scans/min (flag; block at 2×), cumulative hourly spend cap — rate and spend are observed facts, not self-reports. Scoped to the account behind your API key, so a fresh agent_id per request opens no new window; only anonymous scans fall back to agent_id/payer. A payment TollWarden blocks still takes a rate slot but adds nothing to the hourly spend, so a seller's absurd quote, refused at the ceiling, does not lock you out of paying anyone else for the next hour |
| First-contact size cap | First payment to a never-seen counterparty above a threshold |
| Asset verification | asset contract that isn't canonical USDC on the declared network (lookalike-token attack). The network may be a CAIP-2 id or an x402 v1 name (base, base-sepolia, polygon, ethereum); both reach the same check |
| Merchant pinning (TOFU) | Two tiers. Your account's own pin: pay_to rotation on a domain *you* have paid before → block — nobody else can have written that record. Shared observation: the first address *any* caller presented for the domain; a mismatch there is a flag ("another caller saw a different address"), because both sides are client input — it becomes a block only once the non-blocking CDP Bazaar cross-check has verified the pinned address as the domain's merchant. Pin age and the named corroboration sources ship as signed attestation fields (see below), so a wallet can tell a four-minute-old pin from a six-month-old one instead of trusting both equally |
| Address poisoning | pay_to that matches a counterparty you have paid, your own pinned merchant, or a CDP-verified pin on its first + last characters but differs in the middle — the truncated-display ("0x2096…287C") vanity-address attack → block. A lookalike of an address some *other* caller merely presented → flag, so a stranger cannot seed a vanity "pin" and get your honest payment blocked as the lookalike. Also catches bait: a near-copy of the recipient or a trusted address *planted in the content the agent just read*. Blocked payments are rolled back out of trust state, so repeat attempts keep detecting |
| ScoutScore trust signal (opt-in) | Merchant domains rated LOW/VERY_LOW by ScoutScore (spam farms, template clones, dead endpoints) → flag, clearly labeled as an external third-party signal. Lookups are async + cached (zero scan latency), share the domain only, and can never block on their own. Enable with SCOUTSCORE=on |
| Known-bad list | O(1) membership against a curated/synced badlist |
| Deep content analysis | Encoded/obfuscated injection payloads decoded and rescanned: base64 (both alphabets, line-wrapped, space-chunked, double-encoded), hex, percent-encoding, HTML entities, JS/JSON \x/\u escapes, Unicode tag-character smuggling ("invisible ASCII"), zero-width and homoglyph obfuscation (Cyrillic, Greek, IPA, small capitals, dotless-i — plus a mixed-script-word signal for lookalikes the fold table does not know), leetspeak (1gn0re) and letter-spacing (i g n o r e). Every pass is linear in the 200 KB content cap and guarded by a latency test. Bypassed below MICRO_BYPASS_USD (default $0.005) per payment, but drip-resistant: once cumulative scanned spend to a counterparty crosses the same threshold, the deep tier runs an
只显示了开头部分；其余内容请在仓库中阅读