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)
Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
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。
VERIFYAX_API_KEY, VERIFYAX_MCP_LOG_LEVEL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 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.verifyax.com/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"verifyax": {
"command": "npx",
"args": [
"-y",
"@verifyax/mcp-server"
],
"env": {
"VERIFYAX_API_KEY": "your-value",
"VERIFYAX_MCP_LOG_LEVEL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http verifyax https://mcp.verifyax.com/mcpclaude mcp add verifyax --env VERIFYAX_API_KEY=your-value --env VERIFYAX_MCP_LOG_LEVEL=your-value -- npx -y @verifyax/mcp-server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": {
"verifyax": {
"url": "https://mcp.verifyax.com/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"verifyax": {
"command": "npx",
"args": [
"-y",
"@verifyax/mcp-server"
],
"env": {
"VERIFYAX_API_KEY": "your-value",
"VERIFYAX_MCP_LOG_LEVEL": "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": {
"verifyax": {
"type": "http",
"url": "https://mcp.verifyax.com/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"verifyax": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@verifyax/mcp-server"
],
"env": {
"VERIFYAX_API_KEY": "your-value",
"VERIFYAX_MCP_LOG_LEVEL": "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。
ChatGPT 只能连接互联网上的服务器:
https://mcp.verifyax.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
VERIFYAX_MCP_LOG_LEVEL env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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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
注册名称已通过 GitHub 账户 verifyax 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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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:VERIFYAX_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(0.4.0)于31天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, TF Rooms
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.
Live room availability, rates and stay quotes for 12 New Leaf motels in Twin Falls, Idaho.
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。
VerifyAX MCP Server
The official Model Context Protocol (MCP) server for VerifyAX: a cloud-hosted bridge that gives your AI tools secure, real-time access to register agents, generate scenarios, run simulations, and read evaluations on the VerifyAX platform.
Getting started · Supported tools · Security · Deploy your own · Report an issue
The official VerifyAX MCP Server is a bridge between your MCP-compatible AI client and the VerifyAX agent-evaluation platform. Once configured, it lets you register agents, generate scenarios, run simulations, and read evaluations in natural language — without writing API scripts.
With the VerifyAX MCP Server, you can:
It complements (does not replace) the verifyax-api skill: the skill is for developers writing code; the MCP server is for conversational workflows.
The VerifyAX MCP Server works with MCP-compatible clients that support Streamable HTTP or stdio:
| Client | Setup reference |
|---|---|
| OpenAI ChatGPT | Connectors / MCP guide |
| Claude (Claude.ai, Code, Desktop) | Claude MCP docs |
| Cursor | Cursor MCP docs |
| Visual Studio Code (GitHub Copilot) | VS Code MCP docs |
| GitHub Copilot CLI | About Copilot CLI |
| Google Gemini CLI | Gemini CLI MCP docs |
| Amazon Quick Suite | MCP integration guide |
Any client that can connect via mcp-remote can also use the hosted endpoint at https://mcp.verifyax.com/mcp.
[!IMPORTANT]
Claude.ai custom connectors: use _No sign-in_ and an `Authorization` header. This server
authenticates with a VerifyAX API key, not OAuth, so in **Settings → Connectors → Add custom
connector**:
1. URL:
https://mcp.verifyax.com/mcp
2. Authentication: No sign-in — described in the dialog as "for servers that use an API key
instead of OAuth". Leave _Sign in now_ unselected; this server publishes no OAuth metadata, so
an OAuth attempt fails.
3. Under Request headers, add
Authorizationwith the valueBearer sk-ver-api-....
All 17 tools then appear, and Claude.ai lets you set approval per tool (it groups them as 12
read-only and 5 write/delete — worth setting the write/delete group to require approval, since
generate_scenarioandevaluate_agentspend credits).
Requires server 0.3.5 or later: earlier builds matched the
Bearerscheme case-sensitively
and rejected clients that normalise it, which surfaced only as "Couldn't connect to the server."
The
X-VerifyAX-API-Keyheader works with the server but Claude.ai's header field rejects that
name, so use
Authorization.
[!TIP]
For step-by-step Claude setup and how this compares to the VerifyAX skill and SDK, see
docs/using-verifyax-with-claude.md.
Seventeen tools mapped to user intents. Blocking tools poll internally and return only when work completes (typically 30s–5min).
| Area | Tools | Blocking |
|---|---|---|
| Agents | register_agent · list_agents · delete_agent | — |
| Scenarios | list_compatible_tags · recommend_scenario_tags · search_scenario_tags · generate_scenario · list_scenarios · get_scenario · delete_scenario | yes (generate_scenario) |
| Evaluation | evaluate_agent · list_recent_runs · get_run_details · get_evaluation_report · get_run_output | yes (evaluate_agent) |
| Usage | get_usage_summary · preview_run_cost | — |
[!NOTE]
For tool descriptions (what Claude reads to pick a tool) and rationale, see
docs/tool-descriptions.md. Package-level reference:
packages/mcp-server/README.md.
Requirements depend on how you connect.
mcp.verifyax.com)mcp-remote proxyverifyax-mcp-server via npx)VERIFYAX_API_KEY)The npm package exposes two binaries (verifyax-mcp-server and verifyax-mcp-server-http); pass the stdio binary name explicitly when using npx.
Hosted endpoint:
https://mcp.verifyax.com/mcp
Send your VerifyAX API key on the initialize request. The hosted server does not store keys — each client session brings its own.
Cursor (native URL — v0.48+):
{
"mcpServers": { "verifyax": { "url": "https://mcp.verifyax.com/mcp", "headers": { "Authorization": "Bearer sk-ver-api-..." } } } }
Do not add a transport field — Cursor detects Streamable HTTP from the URL. You can also use "X-VerifyAX-API-Key": "sk-ver-api-..." instead of Authorization.
Claude Desktop / clients without native HTTP (`mcp-remote`):
Add to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": { "verifyax": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.verifyax.com/mcp", "--transport", "http-only", "--header", "Authorization:${VERIFYAX_AUTH}" ], "env": { "VERIFYAX_AUTH": "Bearer sk-ver-api-..." } } } }
Use --transport http-only because this server speaks Streamable HTTP only (no legacy SSE). You can also pass X-VerifyAX-API-Key: sk-ver-api-... via --header instead of Authorization.
Restart your MCP client after changing config.
Claude Code:
claude mcp add verifyax --env VERIFYAX_API_KEY=sk-ver-api-... -- npx -y -p @verifyax/mcp-server verifyax-mcp-server
[!NOTE]
The version here is deliberately unpinned, so this command always fetches the current server.
Only the
verifyax-mcpplugin pins an exact
version (
@verifyax/mcp-server@), because a marketplace plugin promises that users
get a new server build only when the plugin version is bumped. Setting up by hand carries no such
promise, so tracking the latest release is the right default. Pin it yourself if you need
reproducibility:
-p @verifyax/mcp-server@0.3.5.
-p … verifyax-mcp-servernames the binary explicitly because the package ships two
(
verifyax-mcp-server,verifyax-mcp-server-http) and neither matches the package name, so a
bare
npx -y @verifyax/mcp-serverfails with "could not determine executable to run".
Claude Desktop:
{
"mcpServers": { "verifyax": { "command": "npx", "args": ["-y", "-p", "@verifyax/mcp-server", "verifyax-mcp-server"], "env": { "VERIFYAX_API_KEY": "sk-ver-api-..." } } } }
Restart the client after changing config, then describe what you want in natural language.
https://mcp.verifyax.com/mcp (remote HTTP) or spawns npx -p @verifyax/mcp-server verifyax-mcp-server (local stdio).只显示了开头部分;其余内容请在仓库中阅读