原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Assertify

作者:romaklym版本 0.4.0i★ –i在你的电脑上运行
注册名称io.github.romaklym/assertify

安装

概览

作者提供的说明(英文原文)

Let AI agents use any website you're logged in to. Sessions stay encrypted on your machine.

PopNx MCP 的三大支柱

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。

它能帮你做什么

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。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 注册中心没有列出需要填写的密钥。

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 …”。

下载作者的 .mcpb 文件

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。

它能做什么

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。

基础检查i

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

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 romaklym 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    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“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32424 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32424 个服务器的 88% 更新
  • 基础检查结果等于或优于此分类中其他 32424 个服务器的 100%

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。

常见问题

Assertify 安全吗?

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。

它需要哪些密钥或代码?

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。

它在我的电脑上运行还是在云端?

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)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.4.0)于4天前进入注册中心。

哪些应用可以使用它?

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。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, BankBridge

替代选择

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

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

BankBridge

作者:bankbridge-money

Works in any MCP agent, including local models. Read-only bank accounts, spending, investments.

在云端运行今天更新
安装

作者的 README

打开 README

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。

Assertify

Let your AI agent use any website you're logged in to.

Log in once. Your session stays encrypted on your machine. Claude, Codex, Cursor and any MCP client can then browse, click, type and read for you.

Quick start · Connect your client · Tools · Security · FAQ


You:    Check my LinkedIn messages and summarize anything from recruiters.

Agent: open_session("linkedin") → click "Messaging" → read_text … You have 3 recruiter messages. The most recent is from Dana at Acme, about a Senior QA role …

✨ Why Assertify

Most sites have no API, or one that can't do what you need. Assertify gives your agent a real browser that is already logged in as you, without ever handing it your password.

  • 🔐 Log in once, by hand. A normal browser window opens; you sign in (2FA, passkeys, SSO all work). The agent never sees your password.
  • 🧳 Encrypted, local, yours. Sessions are AES-256-GCM encrypted with a key in your OS keychain. Assertify itself sends nothing anywhere. There is no server and no account.
  • 🤖 Works with every MCP client. Claude Code, Claude Desktop, Codex, Cursor, VS Code, Gemini CLI, Grok, Windsurf…
  • 👀 See what the agent sees. Every step can come with a screenshot, shown in the chat and saved to disk.
  • 🛡️ Fenced in. Each login is locked to its own domains, so a prompt injection on a page can't walk your logged-in browser somewhere else.
  • 👥 Many accounts per site. Five Gmail accounts? Log in to each; they're named after their emails. Use one, or open them all at once.
  • ✋ Asks before it acts. Buttons that send, post, buy, delete or connect are paused until you say yes. Logins can be made read-only.
  • 🧍 Behaves like a person. Real Chrome, your own browser fingerprint, curved mouse moves, uneven typing and natural pauses. No navigator.webdriver flag.
  • 📎 Uploads files and folders. Photos for a Facebook post, a PDF for an email: the agent clicks the upload button and picks your files, just like you would. Key and password files are always refused.
  • 🪟 Handles pop-ups. Cookie banners are declined for you; "share your contact info" style pop-ups are flagged so the agent decides, or closes them.
  • 🔁 Hands back to you when needed. CAPTCHAs, 2FA prompts and expired logins open in a window for you to finish; the agent then carries on.
  • 🪶 Fast and token-cheap. The agent reads a compact outline ([e12] button "Send"), not raw HTML.

⚙️ How it works

flowchart LR

U(["👤 You"]) -- "log in once per account" --> L["Login window real browser, 2FA works "] L -- "named by email" --> V K[["🔑 OS keychain macOS · Windows · Linux "]] -. key .-> V

subgraph V["🔒 Encrypted vault"] direction LR P1["personal@gmail.com"] P2["work@gmail.com"] P3["shop@gmail.com"] P4["you@company.com LinkedIn "] end

V -- decrypt --> S["⚙️ Assertify server asks before send · buy · delete "] A(["🤖 AI agent"]) <-- "pick one account or all at once" --> S S -- "side by side" --> B

subgraph B["Headless browsers, logged in"] direction LR H1["Gmail · personal@"] H2["Gmail · work@"] H3["Gmail · shop@"] end

classDef person fill:#eef2ff,stroke:#6366f1,color:#1e1b4b classDef safe fill:#ecfdf5,stroke:#10b981,color:#064e3b classDef live fill:#fff7ed,stroke:#f97316,color:#7c2d12 class U,A,L,S person class P1,P2,P3,P4,K safe class H1,H2,H3 live style V fill:#f0fdf4,stroke:#10b981 style B fill:#fffbeb,stroke:#f59e0b

Log in once per account; each one is saved under its email. Your agent then opens one account by name, or every account for a site at once, each in its own logged-in browser. Everything above runs on your computer, on macOS, Windows or Linux.

🚀 Quick start

You need uv:

  • macOS / Linux: curl -LsSf https://astral.sh/uv/install.sh | sh
  • Windows (PowerShell): powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
git clone https://github.com/romaklym/assertify.git

cd assertify uv sync uv run assertify setup

setup downloads the browser (Chromium, about 300 MB, once), checks your keychain, and prints the exact command to connect your AI client. If you skip it, Assertify downloads the browser on first use, or falls back to your installed Chrome or Edge.

Linux notes

  • If the browser won't start, install its system libraries: sudo uv run playwright install-deps chromium.
  • The key goes in Secret Service (GNOME Keyring or KWallet). On a server with no keychain, set ASSERTIFY_PASSPHRASE instead.
  • Logging in needs a screen for the browser window. On a server, log in on your desktop and copy ~/.assertify-mcp over (with the same passphrase), or use ssh -X.

Then save your first login:

uv run assertify login github https://github.com/login

A browser window opens. Sign in, then close the window (or press Enter in the terminal). Done. Your agent can now use GitHub as you.

[!TIP]

You can also just ask your agent: *"log me in to Notion"*. It calls start_login, the window opens, and the session saves when you close it.

🔌 Connect your AI client

Replace /path/to/assertify with where you cloned it (assertify setup prints the exact line for you).

Claude Code

claude mcp add -s user assertify -- uv --directory /path/to/assertify run assertify serve

Claude Desktop

Easiest: download assertify.mcpb and double-click it. Claude Desktop installs it with its icon and handles Python for you.

Or add it to claude_desktop_config.json by hand:

{

"mcpServers": { "assertify": { "command": "uv", "args": ["--directory", "/path/to/assertify", "run", "assertify", "serve"] } } }

</details>

Codex

codex mcp add assertify -- uv --directory /path/to/assertify run assertify serve

or in ~/.codex/config.toml:

[mcp_servers.assertify]

command = "uv" args = ["--directory", "/path/to/assertify", "run", "assertify", "serve"]

</details>

Cursor

~/.cursor/mcp.json:

{

"mcpServers": { "assertify": { "command": "uv", "args": ["--directory", "/path/to/assertify", "run", "assertify", "serve"] } } }

</details>

VS Code (Copilot)

.vscode/mcp.json:

{

"servers": { "assertify": { "type": "stdio", "command": "uv", "args": ["--directory", "/path/to/assertify", "run", "assertify", "serve"] } } }

</details>

Gemini CLI, Grok, Windsurf, Zed and others

Any client that runs local (stdio) MCP servers works. Use this command:

uv --directory /path/to/assertify run assertify serve

For JSON configs, use the mcpServers block shown under Cursor.

🧰 Tools

ToolWhat it does
list_profiles(site?)Your saved logins (name, account email, site), optionally only one site's
start_login(url, profile?) / complete_loginOpen a window for you to log in, then encrypt and save the session. No name: it's named after the account's email
rename_profile · delete_profileRename or remove a saved login
open_session(profile, url?, screenshots?)Start a logged-in headless browser; returns a session_id and a page outline
`open_sessions(site? \profiles?)`Open several logins at once (e.g. every Gmail account), one session_id each
snapshotURL, title and interactive elements as [e12] button "Save"; pop-ups first, warnings for CAPTCHAs and sign-in pages
find(query)Search the whole page for elements by label
click · type_text · select_option · press_key · scroll · back · navigate · wait_forAct by ref or by visible text (click(text="Messages")), so small redesigns don't break a flow; each returns a fresh outline
`upload_files(paths, ref? \text?)`Attach files or whole folders: through the site's file dialog (text="Photo/video"), its upload field, or drag-and-drop. Only attaches; posting is a separate, confirmed click
dismiss_popupClose the pop-up on top with its close / "Not now" button
handoff(reason?)Open the current page in a window for you (CAPTCHA, 2FA, expired login); the session picks up your fresh login
read_textThe visible text of the page, marked as untrusted website content
screenshot(ref?, full_page?)Screenshot of the page or one element, shown to the agent and saved to a file
set_screenshots(enabled)Attach a screenshot to every step (great for watching a run)
switch_tabPopups become the active tab automatically; this switches back
save_session / close_sessionWrite refreshed cookies back to the vault (closing saves by default)
evaluateRun JavaScript in the page. Off unless ASSERTIFY_ALLOW_EVAL=1
👀 Seeing what the agent sees

Ask *"show me a screenshot"* or *"open my GitHub session with screenshots on so I can follow along"*. Images appear in the chat in clients that show them, and every one is saved to ~/.assertify-mcp/screenshots/ /NNN- .jpg. The folder is private to you and cleared after 7 days.

👥 Several accounts on one site

Log in once per account. Leave the name out and Assertify names each login after the email address it finds on the page (falls back to google.com-1, google.com-2… when a site doesn't show one):

assertify login https://mail.google.com   # sign in as you@gmail.com   -> saved as "you@gmail.com"

assertify login https://mail.google.com # sign in as work@gmail.com -> saved as "work@gmail.com" assertify login work https://mail.google.com # or pick the name yourself assertify list google.com # just the Google logins assertify rename google.com-1 side-project

Then just ask:

  • *"Check my work@gmail.com inbox"*: the agent opens that one login.
  • *"Any unread mail in any of my Gmail accounts?"*: the agent calls open_sessions(site="google.com") and gets one session per account, which it can work through side by side.

Each account lives in its own encrypted file and its own isolated browser, so cookies never mix. On sites that restrict automation, avoid running the same action on many accounts at once.

📎 Uploading files

Tell your agent what to upload and where:

*"Post the photos in ~/Pictures/trip to my Facebook with the caption 'Back home'"*

The agent opens the composer, calls upload_files(paths=["~/Pictures/trip"], text="Photo/video"), writes the caption, then asks you before pressing Post. Under the hood:

  1. File dialog first. It clicks the upload button with a natural mouse move and picks the files in

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx