Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Self-hosted MCP server: run OpenAI Codex CLI prompts and manage workspace files.
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。
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": {
"codexbox": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/psyb0t/codexbox:v0.7.6"
]
}
}
}在终端中运行这条命令
claude mcp add codexbox -- docker run -i --rm docker.io/psyb0t/codexbox:v0.7.6粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"codexbox": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/psyb0t/codexbox:v0.7.6"
]
}
}
}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": {
"codexbox": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/psyb0t/codexbox:v0.7.6"
]
}
}
}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6日
注册名称已通过 GitHub 账户 psyb0t 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。
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–,最新版本(0.7.6)于15天前进入注册中心。
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 Docker。
同一分类中有:Context7, Codebase Memory, Exa
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
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
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。
OpenAI Codex CLI inside an aicodebox container. Minimal and toolchain-loaded images, five ways in: interactive shell, one-shot exec, OpenAI-compatible endpoint, MCP server, Telegram bot, and a cron scheduler that fires codex on whatever schedule you want.
You talk to codexbox. codexbox talks to codex. codex talks to OpenAI — or your ChatGPT subscription. Nobody cares about the middle.
codexbox wrapperDocker installed and running is the only prerequisite.
The installer pulls the selected image, creates the persistent Codex and SSH directories, downloads the wrapper, and installs codexbox on your PATH.
# minimal image — default
curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-codexbox/master/install.sh | bash
export CODEXBOX_FULL=1 && curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-codexbox/master/install.sh | bash
curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-codexbox/master/install.sh | bash -s -- codex
Installing with CODEXBOX_FULL=1 bakes latest-full into the wrapper, so the choice persists; you do not need to export it again. CODEXBOX_FULL must be set for bash, not merely for curl, hence the export … && form above.
From a checkout of this repository, build the matching image and install the local wrapper without pulling a published codexbox image:
make install # minimal image
make install-full # full image
make install-wrapper CODEXBOX_FULL=1 make install-wrapper # full image
These targets set CODEXBOX_SRC_LOCAL=true. make install and make install-full build their image first; make install-wrapper only installs the local wrapper.sh against the selected existing image. It fails if that image is absent instead of falling back to docker pull.
The remote installer downloads wrapper.sh from its matching release tag. Automation can set CODEXBOX_INSTALL_DIR, CODEXBOX_BIN_NAME, and AICODEBOX_MANAGED_INSTALL=1 when it installs into a different command directory without prompting to replace an existing SSH key.
codexbox wrapperThe wrapper mounts the current directory as the workspace, persists ~/.codex (so login survives container recreation), forwards auth and configured environment variables, and manages a per-directory container.
export OPENAI_API_KEY=sk-... # or use a subscription: `codexbox login --device-auth`
codexbox # interactive TUI — continues the last session for THIS dir codexbox --no-continue # same, but starts a brand-new session instead codexbox exec "fix the failing test in ./app" # one-shot codex exec, output to your terminal echo "summarize README.md" | codexbox exec - # prompt via stdin codexbox login --device-auth # ChatGPT-subscription OAuth login (persists in ~/.codex) codexbox login status # which auth mode is active codexbox --version # passthrough to codex --version codexbox stop # stop this dir's running container(s) codexbox clear-session # drop codex's saved sessions (keeps auth + config)
The wrapper forwards "$@" straight to the image, so any codex subcommand works (codexbox mcp ..., codexbox doctor, etc.). The sandbox-bypass flag is injected inside the container — you never pass it yourself.
The bare interactive TUI defaults to continuing the most recent session for the directory you're in (same idea as claudebox's default) — codex's own resume --last cwd-scopes the lookup and starts a fresh session automatically when there's nothing to resume, so this is safe on a brand-new workspace too. Pass --no-continue to force a fresh session instead.
Install codexbox, claudebox, and pibox in the same command directory, normally /usr/local/bin, when one box needs to launch another. The wrapper finds sibling wrapper files there and mounts them read-only into the container. A sibling wrapper then runs through the host Docker daemon and mounts its own host data directory. Codexbox does not directly mount another agent's home.
The installed wrapper is the normal interface for people and agents. An agent should run codexbox from the requested workspace instead of assembling a new docker run command. The wrapper preserves the workspace path, Codex state, SSH state, image choice, and per-workspace container lifecycle.
codexbox exec "inspect this workspace and report the failing tests"
CODEXBOX_FULL=1 codexbox exec "run the full test suite" printf '%s\n' "summarize README.md" | codexbox exec -
When one box needs another, install codexbox, claudebox, and pibox in the same command directory. A running box can call the sibling command directly. The parent wrapper passes the host launch context and mounts only the sibling wrapper file. Do not set AICODEBOX_HOST_*, copy a wrapper, or manually mount another box's state directory.
The wrapper does not forward an SSH agent on its own. To give the box your agent, mount its socket and point SSH_AUTH_SOCK at it:
CODEXBOX_MOUNT_SSH="$SSH_AUTH_SOCK:/ssh-agent:ro" CODEXBOX_ENV_SSH_AUTH_SOCK=/ssh-agent codexbox
Every key loaded in that agent becomes usable inside the box.
Use raw Docker only for an explicitly requested container deployment. The wrapper is the normal route for interactive, one-shot, and local service use. The Modes section has the relevant deployment commands and configuration.
psyb0t/codexbox:latest is the default minimal image: Codex, Node.js, Python, uv, Docker, Git, jq, and curl.psyb0t/codexbox:latest-full starts from the shared aicodebox:latest-full base, then adds Codexbox's adapter, entrypoint, auth, and config.CODEXBOX_FULL is binary: the installer defaults to minimal, 0 selects minimal, and 1 selects full. At runtime, an unset value preserves the installed image choice. Any other value fails. The installer writes the resolved image into the installed wrapper, so the choice persists without exporting the variable on every run. A runtime CODEXBOX_FULL=0 or CODEXBOX_FULL=1 temporarily forces a variant; CODEXBOX_IMAGE remains the highest-priority explicit override.
The full image adds:
The full variant inherits the shared Aicodebox full image. Aicodebox owns the shared toolchain pins, locks, and supply-chain checks. Codexbox adds only its agent package and startup layer.
Licensing note: the minimal image is clean — just Apache-2.0 Codex on top of the aicodebox base. The full image additionally bundles HashiCorp Terraform, which is BUSL-1.1 (source-available, non-compete), not OSI-approved open source. If that matters to your use case, stick to the minimal image or review the BUSL-1.1 terms yourself before using latest-full. Full breakdown in THIRD_PARTY.md.
Set CODEXBOX_GIT_NAME and CODEXBOX_GIT_EMAIL on the host to configure the runtime user's global Git identity before startup hooks. Direct container deployments accept the same names. Nonempty AICODEBOX_GIT_NAME and AICODEBOX_GIT_EMAIL inside the container take precedence; through the wrapper, supply those shared values as AICODEBOX_ENV_AICODEBOX_GIT_NAME and AICODEBOX_ENV_AICODEBOX_GIT_EMAIL. Empty settings preserve existing Git config. Multiline values are rejected.
make version V=X.Y.Z synchronizes package metadata, lockfile, the Codex plugin manifest, and the installer's wrapper release ref without committing or tagging. Remote installs download the matching release wrapper unless CODEXBOX_INSTALL_REF overrides it. Updating an image does not update an installed wrapper.
Set these on the host before running codexbox:
| Var | Default | What it does |
|---|---|---|
OPENAI_API_KEY | — | API-key auth (seeded into ~/.codex/auth.json on boot). Not needed for subscription login. |
OPENAI_BASE_URL | — | Point codex at an OpenAI-compatible endpoint |
CODEXBOX_IMAGE | installed image | Override the image the wrapper runs |
CODEXBOX_FULL | installed choice (0 initially) | 0 forces minimal; 1 forces full |
CODEXBOX_DATA_DIR | ~/.codex | Host dir mounted as CODEX_HOME (auth + config + sessions) |
CODEXBOX_SSH_DIR | ~/.ssh/codexbox | SSH key directory mounted into the container (for git over SSH) |
CODEXBOX_MAX_MEM | 10g | Per-container memory limit |
CODEXBOX_CONTAINER_NAME | derived from $PWD | Override the per-workspace container name |
CODEXBOX_ENV_* | — | Forward arbitrary env into the container (prefix stripped: CODEXBOX_ENV_FOO=bar → FOO=bar) |
CODEXBOX_MOUNT_* | — | Mount extra host dirs (/host:/container syntax, or a bare path for same-path-both-sides) |
AICODEBOX_ENV_* | — | Forward a shared environment variable into the launched container, with the prefix stripped |
AICODEBOX_MOUNT_* | — | Mount a shared host directory into the launched container |
AICODEBOX_HOST_* is the versioned nested-launch context used by sibling wrappers. It records host bind-source paths and is set automatically by a wrapper. Do not set it for an ordinary host launch.
CODEXBOX_MODE_CRON=1 + CODEXBOX_MODE_CRON_FILE=/path/cron.yaml codexbox starts the cron scheduler as a long-running background container instead.
Prefer no host install? Everything the wrapper does is plain docker run; see Manual Docker use and Modes.
Foreground modes (API / Telegram / Cron) are mutually exclusive — except CODEXBOX_TELEGRAM_MODE=1 + CODEXBOX_CRON_MODE=1, which run together (cron in-thread inside telegram). API wins if set alongside anything else.
MCP mode (CODEXBOX_MCP_MODE=1) is independent — it coexists with whatever foreground mode is running. In API mode it's mounted at /mcp/ on the API port; in other modes it runs as a sidecar uvicorn on its own port.
Each
只显示了开头部分;其余内容请在仓库中阅读