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)
Vehicle specs, federal recalls, complaints, TSBs, investigations and OBD-II DTC data for AI agents.
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。
CARVECTOR_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": {
"carvector": {
"command": "npx",
"args": [
"-y",
"carvector-mcp"
],
"env": {
"CARVECTOR_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add carvector --env CARVECTOR_API_KEY=your-value -- npx -y carvector-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": {
"carvector": {
"command": "npx",
"args": [
"-y",
"carvector-mcp"
],
"env": {
"CARVECTOR_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": {
"carvector": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"carvector-mcp"
],
"env": {
"CARVECTOR_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 carvectorio 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:CARVECTOR_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(1.1.1)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, HotCodePush
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.
Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.
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。
Give your AI agent real vehicle data. An MCP server that lets Claude, Cursor, ChatGPT, or any MCP-capable client query the CarVector API natively — vehicle specs, representative images, federal recalls, owner complaints, service bulletins, defect investigations, and OBD-II diagnostic trouble codes.
Models hallucinate car data. They invent horsepower numbers, miss recalls filed last week, and guess at what a trouble code means. carvector-mcp gives your agent structured, sourced answers it can cite instead of a confident guess.
npx -y carvector-mcp --key cv_your_key
· MIT · Free tier, no card → carvector.io
1. Get a free API key at carvector.io — 500 requests a month, no credit card.
2. Add it to your MCP client. Most clients use an mcpServers block:
{
"mcpServers": { "carvector": { "command": "npx", "args": ["-y", "carvector-mcp"], "env": { "CARVECTOR_API_KEY": "cv_your_key" } } } }
That's it. Restart your client and ask it about a vehicle.
Prefer a remote server? If your client supports HTTP MCP, skip the install and point it straight at the hosted endpoint:
`json
{ "mcpServers": { "carvector": {
"url": "https://api.carvector.io/v1/mcp",
"headers": { "Authorization": "Bearer cv_your_key" } } } }
`
| Tool | What it returns |
|---|---|
search_vehicles | Matching vehicles by year / make / model, with ids + specs |
get_vehicle | Full specs for one vehicle — engine, drivetrain, body, image, recall count |
get_recalls | Federal recall campaigns for a vehicle — component, summary, consequence, remedy |
get_complaints | Owner-complaint signal for a vehicle — aggregate by component + the most recent complaints *(Pro plan)* |
get_tsbs | Manufacturer service-bulletin index for a vehicle — the fix the dealer already knows about *(Business plan)* |
get_investigations | Federal defect investigations for a vehicle — a leading indicator of recalls *(Business plan)* |
lookup_dtc | An OBD-II code's title, category, severity, and safety/emissions flags |
The agent chains them naturally: search_vehicles to resolve an id, then get_vehicle, get_recalls, get_complaints, get_tsbs, or get_investigations.
You: "Is a P0300 code serious?"
→ carvector.lookup_dtc({ code: "P0300" })
{ "code": "P0300", "title": "Random/Multiple Cylinder Misfire Detected", "category": "Powertrain", "severity": "High", "safety_risk": true, "emissions_related": true }
Your agent answers: *"Yes — P0300 is a high-severity, safety-related misfire code. Don't keep driving on it."* Sourced, not guessed.
The CarVector HTTP API also accepts x402 payments, so an agent with a wallet can call it with no account, no signup and no API key — it pays per request and gets the data back.
0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)curl -i "https://carvector.io/v1/vehicles?year=2020&make=Ford&model=F-150"
Payable endpoints: /v1/vehicles, /v1/vehicles/:id, /v1/vehicles/:id/recalls, /v1/vehicles/:id/complaints, /v1/vehicles/:id/tsbs, /v1/vehicles/:id/investigations, /v1/dtc/:code.
This MCP client does not pay — it uses an API key.
carvector-mcprequires
CARVECTOR_API_KEYand exits without one. x402 is for calling the HTTP API directly. If you
want keyless access from an agent, call the endpoints above rather than going through this
package.
carvector-mcp is an open-source, thin client. It bundles no data — every call forwards to the CarVector API, authenticated with your key. What you get back:
Calls count against your plan's rate limit and show up in your dashboard, exactly like a REST request.
This client is ~150 lines of readable JavaScript — please read them. It:
api.carvector.io (grep index.js, it's the only URL),Bearer header to that host, nowhere else,@modelcontextprotocol/sdk.Your key stays on your machine. Set it via the CARVECTOR_API_KEY env var (preferred); --key works too but, like any CLI argument, is visible in process listings.
MIT. The client is open source; the data is served by CarVector.