Vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
作者提供的说明(英文原文)
Puts Approve/Deny on your phone before an agent acts, and waits for your fingerprint.
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。
LAUTHER_TOKEN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": {
"lauther": {
"command": "npx",
"args": [
"-y",
"lauther-mcp"
],
"env": {
"LAUTHER_TOKEN": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add lauther --env LAUTHER_TOKEN=your-value -- npx -y lauther-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": {
"lauther": {
"command": "npx",
"args": [
"-y",
"lauther-mcp"
],
"env": {
"LAUTHER_TOKEN": "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": {
"lauther": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"lauther-mcp"
],
"env": {
"LAUTHER_TOKEN": "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8日
注册名称已通过 GitHub 账户 csanadymiklos 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:LAUTHER_TOKEN
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(0.1.1)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:Vexa, emailmd, MCP WhatsApp Cloud
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API
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。
Let your coding agent ask you first, on your phone, before it does something you can't undo.
Agent: About to drop and recreate `users` on staging. Approving?
Phone: [ Approve ] [ Deny ] ← optionally behind your fingerprint Agent: APPROVED after 34s. Confirmed by biometric.
Works with Claude Code, Cursor, Windsurf, or anything else that speaks MCP.
Get a token in the Lauther app: Apps → + → New token. Then add the server to your MCP config:
{
"mcpServers": { "lauther": { "command": "npx", "args": ["-y", "lauther-mcp"], "env": { "LAUTHER_TOKEN": "lpt_your_token" } } } }
Nothing to install — npx fetches it. Node 18+.
ask_approvalBlocks until you answer, then tells the agent one of three things:
| Result | What the agent is told |
|---|---|
APPROVED | proceed with exactly what was asked, and nothing further |
DENIED | stop; do not retry, do not find another way |
NO ANSWER | stop — silence is not consent |
That last row is the one that matters. A timeout is not a yes, and the tool says so in words the model has to read.
Options: details for context, require_biometric to demand a fingerprint, timeout_seconds for how long you're willing to wait (default 120).
On waiting. Lauther's API long-polls for at most 25 seconds. Past that this server keeps asking about the *same* notification rather than sending another, so a ten-minute wait still puts one question on your phone — not one every half minute.
send_notificationOne-way: "the migration finished", "the build broke". Takes title, message, priority and url. Only urgent crosses your quiet hours.
It reports what actually happened, including the case worth knowing about: if no device is registered on your account, you're told that rather than given a cheerful success for a notification nobody received.
get_locationAsks you to share where you are, once. You get a prompt on your phone with Share location and Decline; the agent receives one position, as it was when you tapped.
| Result | What the agent is told |
|---|---|
SHARED | latitude, longitude, accuracy in metres, and when it was read |
DECLINED | do not retry and do not find the location another way |
NO ANSWER | silence is not consent; nothing was shared |
EXPIRED | the request lapsed on your phone; nothing was shared |
Options: question (what you see on the prompt), details, require_biometric, timeout_seconds (default 120).
request_photoAsks you for one picture, taken on the spot or picked from your library. The agent gets the link and the image itself, so it can look at it. The link works for 7 days, after which the photo is deleted. If the image cannot be fetched the agent still gets the text and the link.
Same options and the same four outcomes as get_location.
ask_textAsks you a short question and waits for you to type the answer on your phone: a verification code, a choice, a name, a fact only you know. The prompt shows the question and a field, with Reply and Decline. Answers run to 500 characters, so it is for short things.
| Result | What the agent is told |
|---|---|
ANSWERED | exactly what you typed, in quotes |
DECLINED | do not retry and do not get the answer another way |
NO ANSWER | silence is not consent; nothing was sent |
EXPIRED | the request lapsed on your phone; nothing was sent |
Options: question (default "Answer a question?"), details, placeholder (a hint in the field, such as "6-digit code"), require_biometric, timeout_seconds (default 120).
Most models won't reach for an approval tool unless asked. Something like this in your project rules works well:
Before anything irreversible — deploying, deleting data, spending money,
force-pushing, emailing real people, touching production — call ask_approval and wait. Proceed only on APPROVED.
The approval is signed and, when you ask for it, biometric — the answer records *that a person confirmed it*, not merely that something clicked. That is the difference between an audit trail and a log line.
lauther-client — the plain Node client, if you want push and approvals in your own code rather than in an agent.MIT