Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Kill switch + spend guard for AI agents that spend money, across every wallet vendor at once.
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。
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。
选择你使用的 AI 应用,然后复制设置。
COUNTERSIGN_URL, COUNTERSIGN_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
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": {
"countersign": {
"command": "npx",
"args": [
"-y",
"@countersign/mcp"
],
"env": {
"COUNTERSIGN_URL": "your-value",
"COUNTERSIGN_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add countersign --env COUNTERSIGN_URL=your-value --env COUNTERSIGN_API_KEY=your-value -- npx -y @countersign/mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"countersign": {
"command": "npx",
"args": [
"-y",
"@countersign/mcp"
],
"env": {
"COUNTERSIGN_URL": "your-value",
"COUNTERSIGN_API_KEY": "your-value"
}
}
}
}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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"countersign": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@countersign/mcp"
],
"env": {
"COUNTERSIGN_URL": "your-value",
"COUNTERSIGN_API_KEY": "your-value"
}
}
}
}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。
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6日
注册名称已通过 GitHub 账户 countersign-network 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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。
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。
你需要填写:COUNTERSIGN_URL, COUNTERSIGN_API_KEY
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)。
GitHub 仓库最后更新于–,最新版本(0.2.2)于2个月前进入注册中心。
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。
同一分类中有:Spec Driven Development, Remote Desktop Commander, AI Deprecations
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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
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。
The cross-vendor kill switch + spend guard for AI agents — as MCP tools, inside any MCP client.
Countersign is a neutral control plane that holds one policy, one freeze, and one tamper-evident audit ledger across every agent-wallet backend at once. This package exposes it as Model Context Protocol tools, so an agent (or you, from chat in Claude / Cursor) can ask *"may I spend this?"* before acting — and freeze everything in under a second.
| Tool | What it does |
|---|---|
countersign_request_spend | Pre-flight guard — ask whether a spend is allowed *before* touching the wallet (allow / deny / needs_approval). |
countersign_freeze | The kill switch — freeze every agent on every backend at once. |
countersign_apply_policy | Apply one unified policy (caps, allow/deny lists, approval threshold) across all backends. |
countersign_list_agents / countersign_health | See the governed fleet + control-plane health. |
countersign_list_approvals / countersign_approve / countersign_deny | The human-approval queue. |
countersign_ledger | Read + re-verify the append-only, hash-chained audit ledger. |
countersign_unfreeze | Lift a freeze (recover). |
It governs a running Countersign Core. The hosted Core at app.countersign.network is paused since 2026-09-18 and answers 503, so point this at a Core you run yourself. Set:
COUNTERSIGN_URL — your Core, e.g. https://app.countersign.networkCOUNTERSIGN_API_KEY — required when the Core has auth enabledAdd to your MCP config (claude_desktop_config.json, or claude mcp add, or Cursor's mcp.json):
{
"mcpServers": { "countersign": { "command": "npx", "args": ["-y", "@countersign/mcp"], "env": { "COUNTERSIGN_URL": "https://app.countersign.network", "COUNTERSIGN_API_KEY": "csk_…" } } } }
That's it — your agent now has the spend guard and the kill switch.
If Countersign guards your agent, say so — it tells users (and other agents) that spending is governed, and points the next operator at the same kill switch. Drop this in your README:
[](https://countersign.network)
Countersign spreads by being easy to discover wherever agent builders look for tools. The metadata below is ready to submit to the common registries — copy it as-is.
registry.modelcontextprotocol.io / the mcp-registry repo) — entry: {
"name": "io.github.countersign-network/countersign", "description": "Cross-vendor kill switch + spend guard for AI agents that spend money — one policy, one freeze, one tamper-evident ledger across every wallet/card backend.", "homepage": "https://countersign.network", "repository": "https://github.com/countersign-network/countersign", "packages": [ { "registry": "npm", "name": "@countersign/mcp", "runtime": "npx" } ], "license": "Apache-2.0" }
- **[mcp.so](https://mcp.so)** — submit `@countersign/mcp`; category *Finance / Security / Agents*.
npx-launched server; env COUNTERSIGN_URL (default https://app.countersign.network) + optional COUNTERSIGN_API_KEY.[Countersign](https://github.com/countersign-network/countersign) — cross-vendor spend guard + sub-second kill switch + tamper-evident ledger for AI agents that move money (Coinbase, Turnkey, Openfort, Visa card). Testnet.
Standard listing fields:
| Field | Value |
|---|---|
| Server id | countersign |
| Launch | npx -y @countersign/mcp |
| Tools | countersign_request_spend, countersign_freeze, countersign_apply_policy, countersign_list_agents, countersign_health, countersign_list_approvals, countersign_approve, countersign_deny, countersign_ledger, countersign_unfreeze |
| Tags | payments · security · kill-switch · spend-guard · agent-payments · wallet |
Nothing here is auto-submitted — listings are made deliberately by a maintainer.
Apache-2.0. Countersign holds policy/freeze/ledger; it never takes custody of funds. Testnet only.