Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
callx402 MCP server
概览
作者提供的说明(英文原文)
Read-only x402 payment diagnostics: diagnose, evidence, explain, recover, resolve, status. Zero deps
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 0 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: 网店与支付
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 0 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": {
"callx402": {
"command": "npx",
"args": [
"-y",
"callx402"
]
}
}
}在终端中运行这条命令
claude mcp add callx402 -- npx -y callx402或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"callx402": {
"command": "npx",
"args": [
"-y",
"callx402"
]
}
}
}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": {
"callx402": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"callx402"
]
}
}
}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
- ! 注意
作者与仓库一致
发布者(payload-tools)不是仓库所有者(Payloadhq);可能是其他人代为上架的
- … 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“网店与支付”中的其他服务器比较i
- 星标数多于此分类中其他 1749 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 1749 个服务器的 61% 更新
- 基础检查结果等于或优于此分类中其他 1749 个服务器的 39%
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
callx402 MCP server 安全吗?
它在 1 项适用的基础检查中通过了 0 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(1.0.5)于21天前进入注册中心。
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:Spree Commerce: open-source B2B and marketplace ecommerce, Stripe MCP, MCP Cn Commerce
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
Stripe MCP
MCP server integrating with Stripe - tools for customers, products, payments, and more.
MCP Cn Commerce
8 read-only MCP platform entries; support is operation-specific; merchant live acceptance pending
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。
Payload — Developer infrastructure for x402, agent payments, and programmable revenue.
PAYLOAD → VEYLINE (flagship) → CALLX402 (action layer) → REVRULE (separate) → developer products → free utilities.
This repo: callx402 by Payload — the universal action layer into Veyline's x402 infrastructure.
callx402 by Payload
Powered by Veyline. When x402 breaks, callx402.
callx402 is the universal action layer into Veyline's x402 infrastructure. Say what you need done in plain language (or hit an HTTP endpoint) and callx402 routes it to the production system that does the real work: diagnose a broken x402 payment, rescue a failed transaction, route an agent job to the cheapest viable path, resolve settlement state from on-chain evidence, or execute under an explicit budget with fail-closed safety rules.
Why it exists: x402 failures are expensive and opaque. A settlement attempt ends in settlement_pending and nobody knows whether the money moved. A 402 response your wallet misreads. A retry that signs a second authorization for the same intent and pays twice. callx402 exists for exactly those moments: diagnose pins the failure to a stage, rescue triages the incident, resolve settles the question from evidence, route finds the cheapest viable path, execute runs under a hard budget.
Try it (two minutes, no setup, no account):
npm install -g callx402
callx402 status callx402 'complete this job for under $1'
status prints an honest per-subsystem reachability report, no credentials needed. The intent line parses and plans your request, then stops before executing anything: with no live tool endpoint wired it reports "no executable route available", so no money moves. (Use single quotes: in double quotes your shell would eat the $1.)
Free read-only checks against the live Payload rail:
curl https://payload-rail.fly.dev/v1/callx402/actions
curl 'https://payload-rail.fly.dev/v1/callx402/quote?action=diagnose'
The first returns the paid action catalog with prices; the second returns a free price quote for one action. Invoking a rail action is paid per action via checkout (see https://payloadhq.github.io/agents.json); these commands never pay anything.
If it saves you one debugging session, star the repo and read on.
MCP server: connect in 60 seconds
This repo ships a zero-dependency, read-only MCP server (mcp/index.js, node stdlib only, stdio transport) exposing six x402_* diagnostic tools. Nothing here charges, executes, retries, or repays.
git clone https://github.com/Payloadhq/callx402
no npm install needed for the MCP server
Add this block to your MCP client config (replace the path), then restart the client:
| Client | Config file |
|---|---|
| Claude Desktop | claude_desktop_config.json (~/Library/Application Support/Claude/ on macOS, %APPDATA%\Claude\ on Windows) |
| Cursor | ~/.cursor/mcp.json (user scope) or .cursor/mcp.json (project scope) |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
{
"mcpServers": { "callx402": { "command": "node", "args": ["/absolute/path/to/callx402/mcp/index.js"] } } }
Ask the client to list its MCP tools: the six x402_* tools should appear. Per-client notes and the raw stdio test handshake: integrations/mcp-clients/.
Note: all six free MCP tools respond on a clean npm install using conservative local, read-only assessment of supplied evidence. Without an authoritative source they do not verify settlement, access a private ledger, or execute recovery. Existing configured local/remote subsystem integrations remain available.
The relationship
- PAYLOAD = the parent company.
- VEYLINE = production infrastructure for x402 + MCP. The flagship brand.
- CALLX402 BY PAYLOAD = the x402 response/action layer, powered by Veyline. The entry action into Veyline's production infrastructure, not the flagship name. Nothing here renames Veyline.
Discovery path: a developer searching for x402 finds callx402, uses it, and learns Veyline. Payload is not affiliated with the x402 Foundation.
What it does
- Diagnose an x402 or MCP failure
- Rescue a failed transaction (auth-gated)
- Route a paid agent job to the cheapest viable path
- Resolve settlement state from on-chain evidence
- Execute under an explicit budget, with fail-closed safety rules
Behavioral usage language (not trademark claims):
- "Need to diagnose x402? callx402."
- "Need to rescue a transaction? callx402."
- "Need to route a paid agent job? callx402."
- "Need settlement certainty? callx402."
- "Need to execute under a budget? callx402."
Quickstart
1. Install
npm install -g callx402
Or locally in a project: npm install callx402 (the binary is then at node_modules/.bin/callx402).
Fallback, install direct from GitHub:
npm install Payloadhq/callx402
Local development:
git clone https://github.com/Payloadhq/callx402
cd callx402 npm install npm link # exposes the callx402 command
2. First run: what works with zero setup
callx402 status
callx402 'complete this job for under $1'
status is the honest starting point: a per-subsystem reachability report. On a bare npm install it reads 0/15 subsystems reachable, which is expected (see step 3). The intent line plans in plain language and stops before execution, so it is always safe to run; use single quotes so your shell does not eat $1.
Free read-only checks against the live Payload rail (no account, no keys):
curl https://payload-rail.fly.dev/v1/callx402/actions
curl 'https://payload-rail.fly.dev/v1/callx402/quote?action=diagnose'
These return the paid action catalog with prices and a free price quote for one action. Invoking a rail action is paid per action via checkout (machine front door: https://payloadhq.github.io/agents.json); nothing here pays anything.
3. Self-hosted runtime (advanced, optional)
By default every subsystem command routes to the hosted rail — no setup needed. If you prefer to run everything on your own machine, set CALLX402_LOCAL=1 and point CALLX402_V2_ROOT at the v2.0.0 tree (the x402 Paid API Starter Kit, a separate product):
export CALLX402_LOCAL=1
export CALLX402_V2_ROOT=/path/to/x402-paid-api-starter-kit/v2.0.0 callx402 status # now: 15/15 reachable, 0/15 enabled
Without CALLX402_LOCAL=1, these commands use the hosted rail instead — that is the standard path and needs nothing installed beyond the npm package.
(The default is a x402-paid-api-starter-kit/v2.0.0 directory sitting next to your callx402 checkout.)
Subsystems are disabled by default; status names the flag that enables each one. Set a flag, then run its command:
export PAYLOAD_MCP_DOCTOR=1
callx402 diagnose --target 'https://api.example.com/x402/pay'
More examples (each needs its subsystem flag enabled; run callx402 status to see the flag names):
callx402 rescue --incident inc_123
callx402 route --goal 'fetch 100 product prices for under 0.50 USD' callx402 resolve --evidence '{"txHash":"0xabc..."}'
Note the single quotes: the goal text contains $-style amounts that a shell would expand inside double quotes.
Alternative to the local tree: run in remote mode against your own callx402 server (server/index.js):
export CALLX402_MODE=remote
export CALLX402_REMOTE_URL=http://127.0.0.1:8787
JavaScript SDK
const { callx402 } = require('callx402');
const result = await callx402({ intent: 'complete this job for under $1', maxBudget: 1.00, networks: ['base'], assets: ['USDC'], approvalThreshold: 5.00, idempotencyKey: 'job-42', });
Python SDK
import callx402
result = callx402.callx402( intent="complete this job for under $1", max_budget=1.00, networks=["base"], assets=["USDC"], approval_threshold=5.00, idempotency_key="job-42", )
HTTP server
CALLX402_PORT=8787 node server/index.js
curl -X POST http://127.0.0.1:8787/call \ -H 'Content-Type: application/json' \ -d '{"intent":"complete this job for under $1","maxBudget":1.00,"dryRun":true}'
Full HTTP surface: server/openapi.yaml (served live at GET /openapi.json).
Commands
| Command | What it does | ||
|---|---|---|---|
callx402 "natural language intent" | Intent mode: parse, plan, budget-check, route, execute | ||
callx402 status [--json] | Subsystem reachability and flag state | ||
callx402 diagnose [--target ...] | Diagnose an x402 / MCP failure | ||
callx402 rescue --incident | Rescue a transaction (auth-gated) | ||
callx402 route --goal | Route a paid job to the cheapest viable path | ||
callx402 resolve --evidence | Resolve settlement state from evidence | ||
callx402 doctor | Run the MCP doctor checks | ||
callx402 execute --intent [--max-budget N] [--dry-run] | Execute under an explicit budget | ||
| `callx402 monitor [--once\ | --watch]` | Watch subsystem/incident state | |
callx402 preflight | Preflight checks before a paid run | ||
callx402 inspect [--query ] | Inspect capability graph / state | ||
callx402 evidence [--dir ] | Show recorded evidence for an operation (read-only) — MCP/rail only in 1.0.1, not a published CLI command | ||
callx402 explain [--dir ] | Plain-language state assessment for an operation (read-only) — MCP/rail only in 1.0.1, not a published CLI command | ||
| `callx402 recover [--identity \ | --evidence ]` | Safe recovery decision: RECOVERABLE / SAFE_RETRY / HUMAN_REVIEW (read-only) — MCP/rail only in 1.0.1, not a published CLI command | |
| `callx402 config list \ | get \ | set ` | Manage local config |
Subsystem commands (diagnose, rescue, route, resolve, doctor, monitor, preflight, inspect) need the v2.0.0 tree plus the matching feature flag (see "Full subsystem commands" above); without them they exit 3 and do nothing. status, intent mode, and config work with zero setup.
Execution modes
callx402 works out of the box. There are two modes:
| Mode | What it is | Cost | Setup | What you get |
|---|---|---|---|---|
| callx402 CLI — Hosted (default) | The npm package as a lightweight client to the hosted Payload Rail | Free quote, then pay per action (e.g. diagnose $0.10, resolve $0.25 on the x402 path) | npm install callx402 — zero setup | diagnose, resolve, recover, preflight, evidence, explain and more, executed server-side: free quote first, payment verified exactly once on-chain, invocation metered and auditable, result returned. |
| callx402 Runtime — Self-hosted (advanced) | CLI + the v2.0.0 runtime tree (CALLX402_LOCAL=1, CALLX402_V2_ROOT set) | Free | Point CALLX402_V2_ROOT at the x402 Paid API Starter Kit v2.0.0 tree + enable feature flags | Full local execution on your machine against evidence you supply. Read-only analysis; never signs, never retries, never moves money. |
A bare npm install callx402 gives you the hosted mode — no separate tree, no config, no keys. The v2 tree is never required for standard use.
How payment works
Hosted paid actions settle through Payload's signed-redemption flow, not a generic x402 facilitator:
- Get a free quote for the action: the exact price, before any payment.
- Call the action and read the x402 v2
402challenge: USDC on Base, the amount, and thepayToaddress. - Pay the quoted amount to
payTofrom your own wallet. - Redeem the original quote with the paym
只显示了开头部分;其余内容请在仓库中阅读