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

Harness

作者:autonomous-ai版本 0.4.20i★ 1,428i在你的电脑上运行
注册名称ai.autonomous.harness/harness

安装

概览

作者提供的说明(英文原文)

Start Claude Code and Codex agents the person can watch, wait for them and read their answers.

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: 设计、图片与音频

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:3 项中通过 3 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。

你需要

  • npm已安装 Node.js(用于 npx 命令)

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

claude mcp add harness -- npx -y @autonomous-ai/harness-mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "harness": {
      "command": "npx",
      "args": [
        "-y",
        "@autonomous-ai/harness-mcp"
      ]
    }
  }
}

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。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "harness": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@autonomous-ai/harness-mcp"
      ]
    }
  }
}

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7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 harness.autonomous.ai 验证(注册中心会核实域名所有权)

  • ✓ 通过

    仍在维护

    代码最后更新于前天

  • ✓ 通过

    有许可证

    使用 MIT

  • – 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“设计、图片与音频”中的其他服务器比较i

  • 星标数多于此分类中其他 2192 个服务器的 100%
  • 发布到注册中心的时间比此分类中其他 2192 个服务器的 63% 更新
  • 基础检查结果等于或优于此分类中其他 2192 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

Harness 安全吗?

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。

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 仓库最后更新于前天,最新版本(0.4.20)于19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 Node.js, MCPB。

有什么可以替代它?

同一分类中有:Figma Context MCP, Claude Real Video, Figma MCP Server

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

Figma Context MCP

作者:GLips

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

在你的电脑上运行★ 16,165MIT5个月前更新
安装

Claude Real Video

作者:HUANGCHIHHUNGLeo

Let any LLM watch a video locally — and search everything it has ever watched.

在你的电脑上运行★ 2,284MIT2个月前更新
安装

Figma MCP Server

作者:figma

The Figma MCP server brings Figma design context directly into your AI workflow.

在云端运行★ 2,15213个月前更新
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。

Harness like a boss.

The ultimate harness for coding agents and beyond.

Claude Code at work. Codex at home. Hermes in the cloud. One command center.

Start with code. Then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.

Download · How it works · Beyond code · Harnesses · Device

Every agent, side by side

Claude Code, Codex, Cursor, OpenCode, Devin, Amp, Copilot and seven more.

Every machine, side by side

Your laptop, home server and GPU box in one window. Link each one with a password. No SSH keys. No Tailscale. No port forwarding.

Keyboard first

⌘P finds any harness on any machine. ⇧⌘I jumps to the harness waiting on you. ⌘D splits. Every key remaps.

End-to-end encrypted

Code, keys and keystrokes are sealed on your machine. The relay forwards bytes it can't read.

Fast and light

A native app, not Electron. Close it and your agents keep working.

Idle measurements on an M2 Max:

  • ⌘N, ⌘O, ⌘T UI: 11–13 ms median, 15–18 ms p95.
  • Local terminal echo: 1.1 ms median, 7.2 ms p95, excluding UI rendering.
  • Desktop resources: ~0.1% of one CPU core and 304 MiB, including terminal rendering and scrollback; agent CLIs and the daemon are excluded.

Desktop results use a Release fixture with 16 terminals and 1,000 scrollback lines each. See the workflow and resource benchmarks and remote P2P, TURN and relay results for workloads, slow tails, connection failures and raw data.

Built the way developers work
  • Real terminals. Every agent runs in its own tmux pane. Scrollback, colors and keys just work.
  • Your CLIs, as they are. Harness never wraps an agent. It reads transcripts and uses the vendor's own hooks.
  • A worktree per harness. Start an agent on its own branch. Your working copy stays clean.
  • Remap every key. One JSONC file, reloaded on save. Chords up to four strokes.
  • Local models. Run open-weight models on your own machines with Grid, Ollama, MLX-LM and vLLM.
  • Bytes, not pixels. Remote terminals stream text peer to peer. No remote desktop.
  • Open source, all of it. App, CLI, daemon, relay and device, in this repo.

How it works

In the workspace, a harness is one running session of an agent such as Codex or Claude Code, with its own conversation and working context. A tab groups harnesses. Use New Harness to start one and New Tab to group work. Harnesses in the same tab can message each other with harness send: Agent Messages, an experiment of your account, off by default and turned on in Settings ▸ Experimental.

The Store offers harnesses with instructions, tools, and optional viewers for specific crafts. Install a harness, then start it in your workspace. See the Naming System for the complete naming rules.

One daemon per machine runs your agents in tmux. It dials out, so no machine opens a port.

flowchart LR

subgraph laptop["Your laptop"] app["Harness app"] -- loopback --> d1["daemon"] d1 --> a1["tmux · Claude Code · Codex"] end subgraph box["Your GPU box"] d2["daemon"] --> a2["tmux · OpenCode · Hermes"] end device["Harness device"] -- USB --> d1 d1 <-. "direct WebRTC" .-> d2 d1 <-- "ciphertext" --> relay["Harness relay · no keys"] relay <-- "ciphertext" --> d2

Every path is sealed end to end: ChaCha20-Poly1305, X25519 session keys, pinned Ed25519 identities. Harness picks the best path on its own.

Direct. A WebRTC channel between your machines. No server in the path.

Through Cloudflare. When a firewall blocks the direct path, the same encrypted channel runs over Cloudflare's TURN network. Harness keeps trying for a direct path.

Through our relay. A fallback while WebRTC negotiates. The relay holds no keys and forwards ciphertext.

The architecture guide has the details.

Get started

[Download the app](https://harness.autonomous.ai/desktop?utm_source=github&utm_medium=readme) for macOS or Linux.

Add a machine. Run this on it, then Machines → Link Machine in the app:

curl -fsSL https://harness.autonomous.ai/cli/install.sh | bash

harness login harness remote-password set harness start

In a terminal: the same line installs hn — tmux's keys and your ~/.tmux.conf, with every harness on every machine (hn). The first time, hn signs in and connects the computer:

curl -fsSL https://harness.autonomous.ai/cli/install.sh | bash

hn

For agents: Claude Code and Codex can start, wait for and read other harnesses with the harness skill (harness.autonomous.ai/agents, which has the Codex lines too):

claude plugin marketplace add autonomous-ai/openharness --sparse .claude-plugin plugins

claude plugin install harness@openharness

Build from source

Needs Node.js 20+, tmux, Xcode and Flutter 3.47+ / Dart 3.13+:

git clone https://github.com/autonomous-ai/openharness.git

cd openharness (cd cli && npm ci) make install-cli cd desktop flutter config --enable-swift-package-manager flutter pub get flutter run -d macos

make install-cli installs this checkout's CLI and restarts the local daemon. See the development guide.

Beyond code: Build across disciplines

“World-class entrepreneurs are polymaths.” — Peter Thiel

Coding agents can build far more than software. Give one a harness and it works with the real tools of a craft. You steer in a live viewer. Every clip below is a real session.

Beyond code: Design

[Blender](store/agents/blender/). Ask for a lamp and the sliders that matter. Turn them and Blender rebuilds the geometry. Keep the versions you love.

Beyond code: Circuits

[CircuitJS](store/agents/circuitjs/). Build a filter. Change one resistor. Overlay the new trace, measure the difference and keep both.

Beyond code: Robotics

[MuJoCo](store/agents/mujoco/). Pin a moment in a robot's run. Shove it with 100 N. Watch two futures split.

Beyond code: Games

[Godogen](store/agents/godogen/). Your agent makes a playable game. Miss a jump, rewind, try again. Pin the moment so the agent sees what you mean.

Beyond code: Music

[Strudel](store/agents/strudel/). The track is code you can perform. Bring voices in and out, mark the good parts, keep the WAV. Hear it.

Beyond code: Chemistry

[RDKit](store/agents/rdkit/). Turn a bond and watch the molecule move. Follow the real energy curve. Keep the pose worth a closer look.

Beyond code: Documents

[Typst](store/agents/typst/). Your agent writes a real PDF. Circle a detail, quote a line, leave a note. The next draft answers it.

Domain-specific harnesses (DSH)

Code is the common medium. Geometry scripts make parts. Netlists make boards. Animation code makes film.

A domain-specific harness turns a coding agent into a specialist. It brings the craft's instructions and skills, a pinned toolchain, a project template, checks and a live viewer. You chat on one side. The board, the part or the game takes shape on the other.

The agent does the reasoning. The harness supplies the tools and the view. It's a folder with a harness.json, so adding a craft never touches the app.

49 harnesses in the Store

| Engineering | Autonomous Circuit, CircuitJS

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx