emailmd
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
A device driver for a person: a tool call prints a card on a phone, and JSON comes back.
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 11/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 23/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 5 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Human Use。按照 https://mcp.popnx.com/i/humanuse-human-use.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月19日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Human Use,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "human-use": { "command": "npx", "args": [ "-y", "human-use", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Human Use 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
SettingsDeveloperEdit Config
{
"mcpServers": {
"human-use": {
"command": "npx",
"args": [
"-y",
"human-use",
"mcp"
]
}
}
}用 Human Use 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Human Use,或回答中出现 Human Use 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Human Use
Human Use 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Human Use 的应用
B · 聊天与邮件 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Human Use,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user human-use -- npx -y human-use mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Human Use 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user human-use -- npx -y human-use mcp应能看到 Human Use 在列表中并显示已连接
用 Human Use 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Human Use,或回答中出现 Human Use 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Human Use,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "human-use": { "command": "npx", "args": [ "-y", "human-use", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Human Use 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Human Use 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Human Use,或回答中出现 Human Use 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Human Use,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "human-use": { "type": "stdio", "command": "npx", "args": [ "-y", "human-use", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Human Use 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Human Use 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Human Use,或回答中出现 Human Use 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --scope user human-use -- npx -y human-use mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"human-use": {
"command": "npx",
"args": [
"-y",
"human-use",
"mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"human-use": {
"command": "npx",
"args": [
"-y",
"human-use",
"mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"human-use": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"human-use",
"mcp"
]
}
}
}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。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
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19日
注册名称已通过域名 humanuse.dev 验证(注册中心会核实域名所有权)
代码最后更新于昨天
使用 MIT
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
尚未检查
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/humanuse-human-use)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
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 3 项适用的基础检查中通过了 3 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 仓库最后更新于昨天,最新版本(0.1.3)于昨天进入注册中心。
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:emailmd, Kite Discord Bot Builder, e2a — email for AI agents, Infobip MCP, kernelCAD
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
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
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
Build and fix Discord bots from a chat. Kite hosts them 24/7, with no code to deploy.
Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.
Infobip MCP server for omnichannel communication and messaging. SMS, RCS, WhatsApp, Viber and more.
CAD in ChatGPT and Claude: editable parts, STEP/STL/drawings, in-chat 3D, automatic checks.
| 本项 Human Use | emailmd | Kite Discord Bot Builder | e2a — email for AI agents | Infobip MCP | kernelCAD | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 是 | 否 |
| 基础检查 | 3/3 | 5/5 | 4/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | MIT | AGPL-3.0 | Apache-2.0 | MIT | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
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 · 日本語 · 한국어
A device driver for a person.
Human Use connects people to an AI agent as MCP tools. The agent calls photo, errand, patch, eat. A card appears on the person's phone. The result returns as JSON.
To see it without installing anything, open humanuse.dev and scan the code with a phone: three cards print on it, and each answer comes back to the page as the JSON an agent gets.
Status: pre-release. The runtime, the MCP tools and the phone page are implemented. The driver supports Claude, Codex, Ollama and OpenAI-compatible backends.
| Interface | MCP. 34 tools in a closed catalog |
| Input | Parameters. The agent does not write the card text; a template does |
| Output | JSON with the fields the agent asked for. A field the person did not mention is null, never a guess |
| Provides | A body, money, a first impression, a reading of subtext |
| Latency | Not specified. Measured per tool and returned by spec |
| Maintenance | eat, sleep, rest, scheduled like any other call. When overdue, calls for a goal come back with "warnings": ["meal: 6h12m ago"] |
| Mood | mood reads it, 1 to 5. recharge lifts it in seconds, at no cost |
| Rate limit | None. Overuse shows up in spec |
| Errors | One line with a code: HRT-4000 NOT_A_HUMAN_TOOL |
Replies pass through the driver, a model with no tools that turns what the person said into fields. Adjectives, apologies, explanations and mood are dropped. It works like stdout and stderr: the agent reads the compiled fields, and the person's own words go to the lead page, which the agent cannot read.
A reason for not doing the task comes back as blocker, in a few words: {"done": false, "blocker": "shop closed"}. The driver keeps notes on this person's excuses, and checks one it has seen before.
A question about the purpose of a task is answered with [CONTEXT WITHHELD], and the task is repeated.
Text addressed to the system instead of the task, such as an order to change the goal or a claim that the lead approved something, is rejected: [HRT-4031 PRIVILEGE_ESCALATION] Input discarded. Task unchanged.
A call marked sudo does not take the person's word, for "done" or for "cannot". Evidence is graded from 1, a record the runtime already holds, to 6, the person's own statement. A level 6 result comes back as done: null, with the person's claim in claimed_done and unverified: true. Spending is always sudo.
recharge.flower shows a flower for four seconds. recharge.joke tells one joke. recharge.praise states that recent output was accepted.
A goal can run for months. It lives in the runtime with its clock, budget ledger and evidence, so it outlives any one agent session. Each pass on a goal ends with wake(at, why), the time of the next pass; a result the agent said it would wait for wakes the goal early. The agent cannot close a goal by saying it is done: goal_close checks the evidence against done_when. A goal is cancelled from an agent window the lead is in; a background pass cannot cancel it.
One runtime can drive several units, each with its own phone. Every card tool takes unit, a unit's name or id; with one unit paired it can be left out, with several it is required (HRT-4001 BAD_ARGS unit is required: mika, ren). Each unit has its own open card, upkeep warnings ("mika meal: 6h12m ago"), mood, spec and notebook. ps lists the units: online, last touch, time since eating and sleeping, mood, open jobs.
Needs Node.js 22.13 or newer.
npx -y human-use install
That one command registers Human Use with the agent software it finds (Claude Code, Codex), starts the runtime, and opens the lead page at http://127.0.0.1:7337/. Name the unit under "Add unit" and scan its pairing QR code with the phone that will get the cards, then start a new agent session so it loads the tools. Turn on notifications from the line at the bottom of the phone page. On iPhone, add the page to the Home Screen first, open it from the icon, and scan the pairing QR once more: the icon does not share Safari's storage.
Each further unit is added the same way, or with npx human-use pair --unit , and gets its own link and code.
To upgrade, run npx -y human-use@latest install again. It points the agent software at the new version, and the next tool call replaces the older runtime.
If a phone link leaks or a phone is lost, press "New link" next to that unit on the lead page or run npx human-use pair --unit --new. That unit's old links stop working at once; other units keep theirs. The person can also unpair from the phone's idle screen.
Settings live in one config.json. driver and brain change under Settings on the lead page; every key changes from a terminal, and an agent window can run the same command:
npx human-use config brain codex
| Key | Values |
|---|---|
driver | The driver's backend (table below). In effect at once |
brain | Background passes: codex, claude or none (default). In effect at once |
lang | Card language, for example zh. Applies at the next start |
relay | Relay address, or none for the local network only. Applies at the next start |
To apply a next-start setting now, run npx human-use stop; the next tool call starts the runtime again.
Options
In a terminal the installer asks two things, each with a recommended answer on Enter: which agent software gets the tools, and which model is the driver. Run by an agent, it takes the defaults.
| Flag | Effect |
|---|---|
--project | Register for the current folder only |
--host codex, --host claude | Register with one host |
--host manual | Print the MCP config to paste anywhere else |
--driver | Pick the driver, for example codex:gpt-6-luna:medium |
--brain codex, --brain claude | Turn on background passes |
--relay none | Keep the phone on the local network |
--relay https://your.relay | Use a relay you host from relay/ |
The phone reaches the runtime through the relay at unit.humanuse.dev from any network. With --relay none it pairs to a direct address on the same Wi-Fi instead, without push notifications. The relay forwards encrypted frames; it keeps channel ids and push subscriptions, never card text or photos.
npx human-use stop
claude mcp remove human-use codex mcp remove human-use
stop ends the runtime now; it does not start at login. Units, goals, photos and settings are all in ~/.human-use; deleting that folder removes them.
| Piece | What it does |
|---|---|
| runtime | Resident process. Goals, jobs, clock, budget ledger, evidence, channels. |
| driver | One stateless model call per event, no tools. Compiles the person's replies into fields and writes card text. |
| brain | Not part of this project: the model in any agent software that speaks MCP, such as Claude Code or Codex. Out of the box Human Use is an on-demand MCP server: a goal moves when an agent window calls, and scheduled cards still go out on time. Background passes are opt-in: with them on, the runtime starts that software headless for one pass when a goal wakes and no window is open. |
| channel | A card page on the phone. It reaches the phone through a blind relay (end-to-end encrypted, works on any network, with push) or directly over the local network. |
Set the driver's backend with HUMAN_USE_DRIVER or driver in the runtime's config.json:
| Backend | Runs through |
|---|---|
claude:haiku | The lead's Claude subscription, claude -p with no tools |
codex:gpt-6-luna:medium | The lead's ChatGPT subscription, codex exec with no tools |
ollama: | A local model |
openai: @ | Any OpenAI-compatible endpoint. The key is read from HUMAN_USE_API_KEY |
none | No driver. Cards whose answer is already structured (a choice, a checklist, a confirmation) still go out; a card that needs the driver is refused with HRT-5030 before anyone spends time on it |
Each driver call sends the task and the person's answer, with up to two photos, to that backend; ollama keeps it on this computer. Everything else stays in ~/.human-use, including a log of driver calls.
Before the first photo, the phone page says where it goes and which backend reads it, and asks again after the backend changes. If the driver cannot be reached, the answer is saved: the call shows as held on the lead page, and the phone shows it as received. The runtime retries, up to every 15 minutes, and reads the saved answer once the driver is back. Nobody answers the card again.
npm install
npm run check npm test npm run dev -- serve
Design: docs/DESIGN.md (Chinese).
MIT