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)
Install and run open-source OSINT tools in a local sandbox, asking before runs that touch a target.
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 …”。
链接指向作者自己的文件;我们不托管也不重新打包它。打开文件后,Claude Desktop 会进行安装。
在终端中运行这条命令
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。
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
注册名称已通过域名 otinstaller.com 验证(注册中心会核实域名所有权)
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(0.16.1)于13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 MCPB。
同一分类中有:Spec Driven Development, Remote Desktop Commander, FlyDocs
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.
Spec-driven development workflow: your agent works issues, sessions and the status lifecycle.
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。
ot is the OSINT package manager. One command installs, runs, updates or removes any tool in the OTInstaller registry, the largest registry built only for OSINT tools (over 130 of them). No more cloning repositories, fixing Python versions and learning each tool's flags: every tool takes the same typed inputs, runs in a container that can't read your files, and saves its result in the same JSON shape.
Put ot (or ot.exe) somewhere on your PATH. Tools run in containers, so Docker Desktop or Podman must be running; with cosign installed, ot also verifies each image's signature. Then set it up:
ot start # pick starter packs and tools, AI agents and settings, then install
ot doctor # check Docker, cosign, the keychain and the registry
ot start asks at a terminal; ot start --tools --yes does the same from a script, and https://otinstaller.com/start builds the command for you.
ot search email # tools that take an email address
ot run osintverse-community/holehe e:someone@example.com ot runs # every run is saved under ./results; ot runs shows one ot pivot # what to run next on what a run found ot share # a link to the run's results that works for 24 hours
Typed inputs fill the matching input of any tool: u: username, e: email, d: domain, p: phone, ip: IP address and url: URL. Or let ot pick: ot auto someone@example.com runs every installed tool that takes an email address, and on a fresh machine offers to install a bundled playbook's tools first. ot playbook --list shows the playbooks. Tools that need an API key say so; ot keys setup walks you through them, and keys stay in your OS keychain.
--json (or OT_OUTPUT=json) gives JSON output and one-line JSON errors on stderr, and ot never prompts without a terminal. See https://otinstaller.com/docs/automation.ot mcp install claude (or claude-desktop, cursor, vscode, codex, gemini) adds ot's MCP server to your client. Agents ask you before any run that touches a target. See https://otinstaller.com/docs/agents.ot outdated lists installed tools with newer versions and ot update --all installs them. ot self-update installs a new release of ot after checking its signature.
ot counts installs and runs of registry packages, so the registry can show which tools are used and which versions fail. A count carries the tool and its version, how a run ended and how long it took, the container engine, what started it (a command, CI or an AI agent), and your OS, architecture and ot version. It never carries your inputs, targets or results, file paths, run ids, case names, keys or tokens, and tools installed from a local manifest are never counted. The registry keeps daily totals only.
ot telemetry # what is sent, and whether it is on
ot telemetry off # or set OT_NO_TELEMETRY=1 or DO_NOT_TRACK=1 OT_TELEMETRY_DEBUG=1 ot run … # print each count instead of sending it
Turning it off also stops the offer to report a failed run; DO_NOT_TRACK stops the daily update check too. Details: https://otinstaller.com/policy/privacy
Docs: https://otinstaller.com/docs/getting-started · CLI reference: https://otinstaller.com/docs/cli · Bugs and ideas: https://github.com/OTInstaller/feedback/issues · Source: https://github.com/OTInstaller/otinstaller
Licensed under the Apache License 2.0 (LICENSE).