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)
MCP server for Cantrip — AI-powered GTM engine for solo founders
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。
CANTRIP_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": {
"cantrip": {
"command": "npx",
"args": [
"-y",
"mcp-server-cantrip"
],
"env": {
"CANTRIP_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add cantrip --env CANTRIP_API_KEY=your-value -- npx -y mcp-server-cantrip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": {
"cantrip": {
"command": "npx",
"args": [
"-y",
"mcp-server-cantrip"
],
"env": {
"CANTRIP_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": {
"cantrip": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-server-cantrip"
],
"env": {
"CANTRIP_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7日
注册名称已通过 GitHub 账户 ozten 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:CANTRIP_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(1.0.5)于8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, Tools MCP
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.
Web production tools for AI agents: contrast, JP text, WebP, JSON-LD, slugs, dates and 40+ more
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。
Cantrip helps technical founders find their first customers with structured GTM workflows.
Works with Claude Code / Claude Desktop / Cursor — any MCP-compatible agent.
claude mcp add cantrip -e CANTRIP_API_KEY=your-api-key -- npx -y mcp-server-cantrip
"Initialize a Cantrip project for my product: [describe yours in one sentence]"
The Quick start command above covers Claude Code. Verify it worked with claude mcp list or the /mcp command inside a session.
All MCP clients use the same JSON block. Add it to the appropriate config file:
| Client | Config file |
|---|---|
| Claude Code (manual) | ~/.claude.json |
| Claude Code (project-scoped) | .mcp.json in project root |
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Cursor | .cursor/mcp.json (project) or ~/.cursor/mcp.json (global) |
{
"mcpServers": { "cantrip": { "command": "npx", "args": ["-y", "mcp-server-cantrip"], "env": { "CANTRIP_API_KEY": "your-api-key" } } } }
Note: The
-yflag is required — without it,npxprompts for confirmation which hangs over stdio.
Windows (not WSL): Use
"command": "cmd"with"args": ["/c", "npx", "-y", "mcp-server-cantrip"].
Project-scoped with teams: Use
"${CANTRIP_API_KEY}"in the env value so each developer sets the key in their shell profile.
.cantrip.json)Each project directory contains a .cantrip.json file that tells Cantrip which project to target:
{
"project": "my-saas" }
This file is created automatically by cantrip_init (new project) or cantrip_connect (existing project). The agent manages it — you don't need to create it manually.
Multiple projects on the same machine? Each project directory gets its own .cantrip.json. The agent switches context by working in the right directory.
After connecting Cantrip, try these prompts in order:
Server not found / no tools appear:
claude mcp list (Claude Code) or /mcp inside a session to check connection status.~/.claude.json or .mcp.json, not ~/.claude/mcp.json.Server hangs on startup:
-y in the npx args. Without it, npx waits for interactive confirmation that can never arrive over stdio."Cannot reach Cantrip API" errors:
CANTRIP_API_KEY is set in the env block of your MCP config.https://api.cantrip.ai is reachable from your network.Windows "Connection closed" errors:
"command": "cmd" with "args": ["/c", "npx", "-y", "mcp-server-cantrip"].Agent (Claude, etc.) ── MCP protocol (stdio) ──> mcp-server-cantrip ── HTTPS POST ──> https://api.cantrip.ai
The MCP server is a thin translation layer. It converts MCP tool calls into {command, args, flags} JSON envelopes and POSTs them to the Cantrip API. Zero business logic — identical contract to the CLI and React UI.
| Tool | Description |
|---|---|
cantrip_connect | Connect workspace to a project (reads/writes .cantrip.json) |
cantrip_status | Check if the daemon is running |
cantrip_init | Create a new project and auto-connect |
| Tool | Description |
|---|---|
cantrip_snapshot | Project overview, drill into entity types |
cantrip_next | List gap-analysis opportunities |
cantrip_next_prompt | Generate a context-rich LLM prompt for an opportunity |
cantrip_next_run | Spawn a background agent for an opportunity |
cantrip_history | Query the audit trail |
| Tool | Description |
|---|---|
cantrip_review | List items pending review |
cantrip_review_accept | Accept an inferred entity |
cantrip_review_reject | Reject an inferred entity |
cantrip_review_resolve | Resolve an escalation |
cantrip_review_dismiss | Dismiss an escalation |
| Tool | Description |
|---|---|
cantrip_entity_list | List entities of a type |
cantrip_entity_show | Show entity detail |
cantrip_entity_add | Create a new entity |
cantrip_entity_edit | Edit an existing entity |
Supported entity types: icp, pain_point, value_prop, experiment, channel, competitor, contact
MIT