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)
Post a project brief & publish cases on GPTaria from Claude Code, Cursor or Windsurf.
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。
GPTARIA_API_KEY, GPTARIA_BASE_URL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": {
"gptaria": {
"command": "npx",
"args": [
"-y",
"gptaria-mcp"
],
"env": {
"GPTARIA_API_KEY": "your-value",
"GPTARIA_BASE_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add gptaria --env GPTARIA_API_KEY=your-value --env GPTARIA_BASE_URL=your-value -- npx -y gptaria-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": {
"gptaria": {
"command": "npx",
"args": [
"-y",
"gptaria-mcp"
],
"env": {
"GPTARIA_API_KEY": "your-value",
"GPTARIA_BASE_URL": "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": {
"gptaria": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gptaria-mcp"
],
"env": {
"GPTARIA_API_KEY": "your-value",
"GPTARIA_BASE_URL": "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。
GPTARIA_BASE_URL 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。
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 gptaria-mcp 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:GPTARIA_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(0.2.1)于4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, MCP Server Autocad Lisp Helper
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.
High-precision static analysis and debug server for AutoCAD AutoLISP (.lsp) files.
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。
GPTaria MCP connects your AI assistant — Claude Code, Claude Desktop, Cursor, Windsurf — to GPTaria and runs the whole flow straight from your editor: post a project brief, respond with a working prototype, message the other party, publish portfolio cases, and buy access — 23 tools. An MCP (Model Context Protocol) server for the GPTaria REST API.
list_services (free) lists exact prices.get_balance and list_services are free. You always confirm any payment.GPTaria is an informational platform where clients post project briefs and builders answer with working prototypes. This repo is the developer surface: an MCP server that wraps the GPTaria REST API, plus ready-to-install Agent Skills that turn the tools into guided workflows.
REST API → MCP server → Agent skills
(foundation) (AI tools) (guided workflows)
| Tool | For | What it does |
|---|---|---|
list_projects | anyone | List open projects (briefs) you can respond to |
list_responses | clients | List a project's responses, to work on them in your own AI |
list_my_responses | builders | Projects you responded to, with status + win/offer flags |
list_project_comments | anyone | List a project's client clarifications |
get_response_thread | builders | Your own response's timeline (comments + versions) |
list_conversations | anyone | Your message inbox (unread counts, last message) |
get_conversation | anyone | One conversation's timeline (in your language) |
get_balance | anyone | Free — AI-token balance + access status |
list_services | anyone | Free — the shop price list (in ₴) |
create_project | clients | Publish a project brief via a Pro order |
create_project_comment | clients | Add a public clarification to your own project |
create_response | builders | Submit a response (proposal) to a project |
post_proposal_update | builders | Post an updated offer / comment in your thread |
create_case | builders | Publish a portfolio case (draft by default) |
generate_case_summary | builders | Generate a case's AI summary block |
update_profile / get_profile | anyone | Edit / read your own public profile |
offer_project / accept_project / decline_project | client / builder | The offer→accept handshake |
send_message / mark_conversation_read | anyone | Message the other party |
buy_service | anyone | Free tool — buy an access pass / AI pack / secret mode / case verification (returns a checkout link) |
Every tool enforces the same rules as the website — account role, active access pass, the Super-Expert window, and payment where required. There is no bypass path; test against a sandbox key first.
GPTARIA_API_KEY.gptaria_live_…gptaria_sbx_… — validate every call against the real rules but never persist ({ "dry_run": true }). Debug safely, then switch to live. https://www.gptaria.com/api/mcp?api_key=YOUR_KEY npx -y gptaria-mcp with GPTARIA_API_KEY in the server's env (Claude Code, Cursor, Windsurf).See docs/getting-started.md for the exact config per client, and for the full 23-tool reference.
skills/ into your assistant's skills directory.No MCP? Every endpoint is a plain REST call too — see docs/api.md and examples/curl.md.
In Claude Code, add this repo as a plugin marketplace and install it — the MCP server (from npm) and the skills come together:
/plugin marketplace add gptaria-mcp/gptaria-mcp
/plugin install gptaria-mcp
Set GPTARIA_API_KEY in your environment first.
mcp-server/ — the MCP server (Node, stdio) and its setupskills/ — three Agent Skills (publish a project, submit a response, publish a case)docs/ — getting started, REST API reference, the Pro order flowexamples/ — MCP client config + curl examples| Channel | How |
|---|---|
| npm | npx -y gptaria-mcp (or npm i -g gptaria-mcp) — see getting started |
| Claude Code plugin | /plugin marketplace add gptaria-mcp/gptaria-mcp → /plugin install gptaria-mcp |
| From source | clone, cd mcp-server && npm install && node index.mjs |
Distribution manifests live in the repo: server.json (MCP registry), .claude-plugin/ (Claude Code), smithery.yaml (Smithery).
MIT © GPTaria