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

codex-bridge

作者:xallindrome-labs版本 0.1.0i★ –i在你的电脑上运行
注册名称io.github.xallindrome-labs/codex-bridge

安装

概览

作者提供的说明(英文原文)

Lets Claude Code consult the Codex CLI for plans and images, as durable background jobs.

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)。
  • 需要你自己填写: CODEX_BIN, CODEX_BRIDGE_HOME, CODEX_BRIDGE_IDLE_TIMEOUT_MS, CODEX_BRIDGE_PLAN_MODEL, CODEX_BRIDGE_PLAN_EFFORT, CODEX_BRIDGE_IMAGE_MODEL, CODEX_BRIDGE_IMAGE_EFFORT

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 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "codex-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@xallindrome-labs/codex-bridge"
      ],
      "env": {
        "CODEX_BIN": "your-value",
        "CODEX_BRIDGE_HOME": "your-value",
        "CODEX_BRIDGE_IDLE_TIMEOUT_MS": "your-value",
        "CODEX_BRIDGE_PLAN_MODEL": "your-value",
        "CODEX_BRIDGE_PLAN_EFFORT": "your-value",
        "CODEX_BRIDGE_IMAGE_MODEL": "your-value",
        "CODEX_BRIDGE_IMAGE_EFFORT": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add codex-bridge --env CODEX_BIN=your-value --env CODEX_BRIDGE_HOME=your-value --env CODEX_BRIDGE_IDLE_TIMEOUT_MS=your-value --env CODEX_BRIDGE_PLAN_MODEL=your-value --env CODEX_BRIDGE_PLAN_EFFORT=your-value --env CODEX_BRIDGE_IMAGE_MODEL=your-value --env CODEX_BRIDGE_IMAGE_EFFORT=your-value -- npx -y @xallindrome-labs/codex-bridge

运行前请先填写空着的值。

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": {
    "codex-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@xallindrome-labs/codex-bridge"
      ],
      "env": {
        "CODEX_BIN": "your-value",
        "CODEX_BRIDGE_HOME": "your-value",
        "CODEX_BRIDGE_IDLE_TIMEOUT_MS": "your-value",
        "CODEX_BRIDGE_PLAN_MODEL": "your-value",
        "CODEX_BRIDGE_PLAN_EFFORT": "your-value",
        "CODEX_BRIDGE_IMAGE_MODEL": "your-value",
        "CODEX_BRIDGE_IMAGE_EFFORT": "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。

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": {
    "codex-bridge": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@xallindrome-labs/codex-bridge"
      ],
      "env": {
        "CODEX_BIN": "your-value",
        "CODEX_BRIDGE_HOME": "your-value",
        "CODEX_BRIDGE_IDLE_TIMEOUT_MS": "your-value",
        "CODEX_BRIDGE_PLAN_MODEL": "your-value",
        "CODEX_BRIDGE_PLAN_EFFORT": "your-value",
        "CODEX_BRIDGE_IMAGE_MODEL": "your-value",
        "CODEX_BRIDGE_IMAGE_EFFORT": "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。

需要你填写的值

  • CODEX_BIN env
    Path to the Codex CLI binary. Auto-detected when unset.
  • CODEX_BRIDGE_HOME env
    Where job files are stored. Default: ~/.codex-bridge
  • CODEX_BRIDGE_IDLE_TIMEOUT_MS env
    Stop a run after this many ms with no Codex output. Default: 600000
  • CODEX_BRIDGE_PLAN_MODEL env
    Model for codex_plan. Default: your Codex config.
  • CODEX_BRIDGE_PLAN_EFFORT env
    Reasoning effort for codex_plan. Default: your Codex config.
  • CODEX_BRIDGE_IMAGE_MODEL env
    Model for codex_image. Default: gpt-6-luna
  • CODEX_BRIDGE_IMAGE_EFFORT env
    Reasoning effort for codex_image. Default: high

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 GitHub 账户 xallindrome-labs 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 32712 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32712 个服务器的 71% 更新
  • 基础检查结果等于或优于此分类中其他 32712 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

codex-bridge 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(0.1.0)于16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。

有什么可以替代它?

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

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前天更新
安装

Aiterm MCP

作者:kitepon

Persistent terminals and one launcher for Claude, Codex, Grok, Cursor, and Antigravity harnesses.

在你的电脑上运行今天更新
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。

codex-bridge

Codex jobs for Claude Code that survive crashes, closed windows and reboots, with Codex image generation built in. A dependency-free MCP server built Windows-first: every call is a job saved on disk, so you can close Claude, lose power, or kill a process, and pick the work up again with codex_resume.

Roles: Claude Code implements. Codex plans and builds images. Optionally (opt-in, one folder), Codex can also write code while Claude reviews: see Let Codex write code. And an optional pane beside the chat lists your jobs live and shows your Codex usage and when it resets: see Codex jobs pane.

The server calls in this recording are real (Codex at effort: low, idle time trimmed); the claude mcp add line is scripted. The raw recording is docs/demo.cast; play it with asciinema play docs/demo.cast.

Quickstart

You need Node.js 20 or newer and the Codex CLI installed and logged in.

claude mcp add codex-bridge -- npx -y @xallindrome-labs/codex-bridge

Restart Claude Code, then ask it something like *"Get a plan from Codex for adding rate limiting, in the background, and keep going"*. Claude will call codex_plan with background: true and collect the answer later.

Other MCP clients: run npx -y @xallindrome-labs/codex-bridge as a stdio server.

Platform note: developed and tested on Windows 11, where real Codex jobs have been run. CI checks on Linux, macOS and Windows (Node 20 and 22) that the server starts, speaks MCP and works when installed from the npm tarball, and on Linux and macOS that jobs run, finish and survive the server being killed, using a fake codex. CI has no real Codex CLI, so real Codex jobs on macOS and Linux are untested. Reports and fixes are welcome.

ToolWhat it doesSandboxDefault model / effort
codex_planCodex writes implementation plans, design reviews and second opinions. It inspects the project in cwd.read-only (always)Your Codex config defaults
codex_imageCodex generates or edits images. The bridge copies each one into output_dir as soon as it's made.read-only (always)gpt-6-luna / high
codex_codeOff by default. Codex implements a change by editing files in one folder you choose. See below.workspace-write, that folder only, no networkYour Codex config defaults
codex_resultGets a job's result or progress (wait_seconds up to 240), or lists recent jobs.
codex_resumeContinues an interrupted, timed-out or failed job from where it stopped.
codex_cancelStops a running job.

codex_plan, codex_image and codex_code accept:

  • effort: low, medium, high, xhigh, max or ultra (Luna supports up to max).
  • model: overrides the default model for that call.
  • background: true: returns a job_id immediately so Claude can keep working.
  • session_id: continues an earlier Codex thread, for example "make the icon darker".

codex_image also takes count, the number of images wanted. Set it for batches: it enables k/count progress and resumes that ask for exactly the missing images.

Let Codex write code (opt-in)

By default Codex can only read. If you want it to implement things while Claude reviews, name the one folder it may edit:

claude mcp add codex-bridge -e CODEX_BRIDGE_WRITE_ROOT=/path/to/your/project -- npx -y @xallindrome-labs/codex-bridge

Restart Claude Code and a fourth tool, codex_code, appears. Ask for it in plain words: *"Have Codex implement the plan in the background, then review its diff."*

  • One folder. cwd must be CODEX_BRIDGE_WRITE_ROOT or inside it. Anything else is refused, checked on real paths so .. and symlinks don't escape. A drive root or your home folder is refused as too broad.
  • No network, no commits. Codex runs with network access off and is told to leave changes uncommitted so you can see them in git diff. The no-commit rule is a prompt, not a sandbox rule.
  • Claude reviews. Every codex_code result ends with a reminder to read the diff before accepting it. A failed or cancelled run says Codex may have left partial edits.
  • Same job machinery. It survives restarts, background: true and codex_resume work the same way, and a resume re-checks the folder rule.
  • Temp files. In our test on Windows 11, writes outside the folder and network access were blocked, but the system temp folder stayed writable. Treat temp as writable. CODEX_BRIDGE_WRITE_ALLOW_TMP=1 stops asking Codex to block it.
  • Don't edit the same files yourself while a codex_code job runs.

Unset the variable and restart, and the tool is gone; codex_plan and codex_image are always read-only.

Codex jobs pane

An optional add-on that opens a pane beside the Claude Code chat listing your Codex jobs live: running, done, interrupted, with age, request and images k/n for batches. It also shows your Codex usage: the 5-hour and weekly windows, percent used, when each resets, and how many images were generated in each (Codex has one shared meter, so images use the same limits). It only reads the job files on disk, so it shows jobs from any session, including ones that kept running after you closed Claude. It also puts codex: N running in the status line and shows a toast when a job you watched finishes.

At the prompt of a terminal Claude Code session:

/plugin install codex-jobs --marketplace xallindrome-labs/codex-bridge

In the desktop app, where /plugin does not run: click + next to the prompt box, then Plugins, Add marketplace with xallindrome-labs/codex-bridge, then Add plugin. Without a marketplace, for one session: claude --plugin-dir "$(npx -y @xallindrome-labs/codex-bridge --pane-path)".

Then type /codex-jobs. It also opens by itself the first time a job is running in a session. Details and how it works are in plugins/codex-jobs. It needs a Claude Code build that supports mods; it is tested against the engine's own test kit, not every surface's paint.

How it compares

OpenAI's codex-plugin-cc is the official way to use Codex from Claude Code, and it's good at what it does: slash commands for review and rescue. codex-bridge is an MCP server instead, with a different focus: jobs that don't get lost, and images.

Several open issues in the plugin's tracker are about jobs getting lost, and codex-bridge is designed to avoid each of them. These come from reading the designs, not from a head-to-head test:

Reported in codex-plugin-ccHow codex-bridge handles it
Background job shows "running" forever after its worker dies (#704, #699)Status is worked out from files on disk plus a heartbeat and a process check. A dead runner shows as interrupted, never "running", and codex_resume continues it.
Windows cancel silently fails (#708)Cancel writes a marker file; the runner that owns the Codex process sees it within about 2 seconds and stops the process tree by calling taskkill.exe directly, with no shell in between.
Windows broker processes leak (#718, #782)There is no shared broker. Each attempt is one runner process that exits when Codex does.
One session ending kills other sessions' jobs (#671)Runners are started outside Claude's process tree (via WMI on Windows), so closing a session can't take them down.

What the plugin does that this doesn't: slash commands, and its review-gate and rescue workflows. And this one is newer, with far fewer users. If the plugin works for you, keep using it. If you've lost jobs, or want Codex to generate images that survive a crash, try this.

Jobs survive restarts

Every call is a job saved under ~/.codex-bridge/jobs/ /, including calls that aren't run in the background.

  • Claude closes or crashes: the job keeps running. server.mjs starts runner.mjs through WMI (Win32_Process.Create), so the job isn't part of Claude Code's process tree. Closing Claude can't kill it, and any later Claude session can collect it with codex_result.
  • The job itself dies (reboot, power loss, Codex crash, or killed process): the job is marked interrupted. The next Claude session is told about it when it starts. codex_resume continues it:
  1. It copies out any images generated just before the interruption.
  2. It resumes the same Codex thread: "N are already done, generate only the remaining ones."
  3. If no Codex thread had started yet, it reruns the original request.

How images are collected

Codex never writes image files. Its image tool stores every generated image in ~/.codex/generated_images/ /. The runner checks that folder every 2 seconds and copies new images into output_dir as .png, -2.png, and so on, in the order they were made. copied.json in the job folder records what has been copied, so an image is never copied twice across attempts.

This gives three benefits:

  • Image jobs run in a read-only sandbox.
  • A crash loses at most the one image being generated.
  • Resume counts exactly what's done.

It also avoids a real problem: when Luna was allowed to save files itself, it re-typed each image as base64 through dozens of shell commands. That was slow, and the saved file no longer matched the original.

  • Codex stalls: the runner stops a run after 10 minutes with no output. The job is marked timed_out, and it can be resumed.

Each attempt keeps its own prompt.txt, events.jsonl (the Codex event stream), stderr.txt, heartbeat and result.json. Finished jobs are deleted after 14 days.

How it works

Each attempt runs codex exec --json (or codex exec resume ) with the prompt on stdin. No shell is involved.

Every call runs read-only, except codex_code when you have opted in (it runs workspace-write in your one folder, with network off). New sessions pass -s read-only plus -c sandbox_mode="read-only"; resumed sessions pass -c sandbox_mode="read-only" (codex exec resume takes no -s). Your Codex config may default to danger-full-access, but that default never applies to bridge calls. The plan smoke test checks that a write attempted from a resumed session fails.

FileRole
server.mjsThe MCP server. It creates jobs, launches runners, works out job status from the files on disk, and handles resume and cancel.
runner.mjsRuns one attempt: starts Codex, records the heartbeat, watches for a stall or cancellation, collects images and writes result.json.
lib.mjsShared helpers: finding the Codex binary, building arguments, parsing events, handling images.

Install options

# for all your projects

claude mcp add -s user codex-bridge -- npx -y @xallindrome-labs/codex-bridge

or from a local checkout

claude mcp add codex-bridge -- node /path/to/codex-bridge/server.mjs

Remove it with claude mcp remove codex-bridge (add -s user if you installed it that way).

Configuration (env vars)

VarDefault
CODEX_BINAuto-detected. It prefers a codex.exe next to codex-code-mode-host.exe, which is currently ~/.codex/plugins/.plugin-appserver/codex.exe.
CODEX_BRIDGE_HOME~/.codex-bridge

| CODEX_BRIDGE_IDLE_TIMEOUT_MS | `600

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx