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)
Free proxies that actually work: checked HTTP/SOCKS proxies, and pages fetched through them
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。
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": {
"proxy-scraper": {
"command": "uvx",
"args": [
"proxy-scraper-cli"
]
}
}
}在终端中运行这条命令
claude mcp add proxy-scraper -- uvx proxy-scraper-cli粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"proxy-scraper": {
"command": "uvx",
"args": [
"proxy-scraper-cli"
]
}
}
}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": {
"proxy-scraper": {
"type": "stdio",
"command": "uvx",
"args": [
"proxy-scraper-cli"
]
}
}
}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 maximilianfeix 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。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
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(1.31.0)于14天前进入注册中心。
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 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, zanadir
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.
Find what a repository's CI is missing, and which security checks cannot fail the build.
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。
English · 简体中文 · Español · Deutsch · Русский · Português (Brasil) · Français
Install · Live list · Check states · For AI agents · Proxy server · Recipes · Options · FAQ · All docs
Proxy checks you can inspect: what passed, what failed, and when. proxy-scraper collects public HTTP, SOCKS4 and SOCKS5 proxies from hundreds of lists, runs up to four checks on each one and keeps the outcome of each check for the proxies it lists (for the rest it counts how each check ended), so "working" is something you can look at instead of a label you have to trust.
https://github.com/user-attachments/assets/b99c1d8f-5bce-4a52-a8a9-b9c2c726301b
21 seconds · real interface, example numbers, documentation IPs · mp4
Try it – no install needed, uvx comes with uv (pipx run does the same):
uvx proxy-scraper-cli --pick 3 --verify # up to 3 proxies from the hourly list that pass right now, from your network
uvx proxy-scraper-cli --diagnose socks5://HOST:PORT # one proxy, check by check: what it did and what it didn't
A real terminal recording, made against six simulated proxies on localhost (reproduce it). It shows how results are reported. It measures nothing about public proxies.
The package is proxy-scraper-cli on PyPI (the plain name is taken). Once installed, the command is proxy-scraper. --verify and --diagnose need version 1.30 or newer.
Three ways to get proxies, and what "checked" means for each:
| Command | Where the proxies come from | Checked | Takes |
|---|---|---|---|
proxy-scraper --pick 5 | the published list | from GitHub's servers when the list was built, about every hour | under a second |
proxy-scraper --pick 5 --verify | the published list | now, from your network | seconds to a minute and a half at most |
proxy-scraper -y | every list the tool knows | now, from your network | minutes (about three in the hourly runs) |
What you get
passed, failed, unavailable or skipped, with a reason code, the target and the time, in the terminal, in JSON and from Python. A check that didn't run is never shown as passed, and a check target that is down doesn't turn the proxies checked against it into failures. → Check states--pick --verify checks a few proxies from your own network, usually in seconds. --recheck does the same for a list of your own, and --diagnose tells you why one proxy doesn't work.What it can't do. Free proxies are run by strangers, and of one hour's list only about a quarter is on the list again a day later. A pass is one measurement, from one network, against test targets: it is not a promise for the next hour or for the site you care about. The HTTPS check is a verified TLS connection to one test host, not a security rating. Use free proxies for public data and testing, never for logins, payments or anything personal. → What the numbers show and what they don't · Why free proxies fail · How it compares · Who runs free proxies
Only want the lists? You don't need this tool: free-proxy-list has them as plain files per protocol and country, rebuilt about every hour. Or straight from here: all.txt · http.txt · socks4.txt · socks5.txt · proxies.json · more formats
Used by: the hourly list is a built-in source of monosans/proxy-scraper-checker and gfpcom/free-proxy-list.
With [pipx](https://pipx.pypa.io/) (recommended – gives you a proxy-scraper command in its own environment):
pipx install proxy-scraper-cli
proxy-scraper
With [Homebrew](https://brew.sh) on macOS and Linux:
brew install maximilianfeix/tap/proxy-scraper
The formula follows each release within about a day.
Docker, pip, a faster event loop, the latest main, tab completion and where state and results are stored: every other way to install.
Started without arguments, a wizard asks what you are looking for – a preset (find everything, browsing, maximum anonymity, fast, a few right now, recheck, proxy server right away, …) or step by step: the wizard and its presets.
Keys: ↑ ↓ select · Space toggle · 1 – 9 jump · Enter next · Esc back · q quit. In scripts and cron jobs the wizard never shows up – pass options or -y.
Don't want to scan yourself? About every hour GitHub Actions runs the tool and publishes the hits to the proxy-list branch – every entry passed the first request, the second request and the content check in the last run (the HTTPS test is recorded per entry, not required), best first: fast ones that are likely to still be up come on top.
Just want the lists? They also live in a repository of their own, [maximilianfeix/free-proxy-list](https://github.com/maximilianfeix/free-proxy-list) – one list per protocol, per country and per site, updated every hour, with the numbers of the last run on the front page. Watch or star it to keep it at hand. Other tools pull it too: monosans/proxy-scraper-checker and gfpcom/free-proxy-list use it as a built-in source.
→ [Browse it on the website](https://proxy-scraper.de/) – search, filter by type, country, HTTPS, provider and latency, see how long each proxy has been on the list and in how many of the week's runs, copy or download exactly the proxies you need.
Every protocol and country also has its own page with a plain download, e.g. SOCKS5 or Germany (country/de/proxies.txt).
| List | Format | Link |
|---|---|---|
| All | socks5://1.2.3.4:1080 | all.txt |
| HTTP · SOCKS4 · SOCKS5 | 1.2.3.4:8080 | http.txt · socks4.txt · [socks5.txt](https://raw.githubusercontent.com/maximilianfeix/prox
只显示了开头部分;其余内容请在仓库中阅读