fwerkor/local-shell-mcp
使LLM能够使用CLI环境。
Project Overview项目介绍
local-shell-mcp is an MCP protocol-compliant control plane that grants LLM clients controlled access to a local execution environment with shell, file management, browser automation, and remote machine control. It ships with a DSH bundle manifest, so it can be installed directly as a bundle on DeepSeek Harness, while also supporting ChatGPT Developer Mode and any other MCP-compatible client. You can deploy it multiple ways, including via Docker, precompiled standalone binary, Python package, or VS Code extension. To install it via Python, you can run pipx install local-shell-mcp and start it with the short lsm command.
Developers use this tool to give LLMs a sandboxed local execution environment, letting the model handle routine development tasks like running unit tests, debugging broken code, building full projects, and checking application logs. It can also connect to remote machines behind internal firewalls or NAT gateways, allowing the connected LLM to complete custom tasks on those remote devices. It is designed for developers who need to give LLMs real local execution capabilities, as well as users who want to add powerful local tooling to their existing AI agent client.
This project requires Python 3.11 or a newer stable version, and is released under the permissive MIT open-source license for both personal and commercial use. It includes multiple built-in safety protections, such as workspace scoping, command timeouts, sensitive information filtering, and full audit logging for all operations. Because it exposes high-privilege capabilities to connected LLMs, users must follow the documented hardening rules, and it is strongly recommended to run the service inside an isolated container or virtual machine to avoid unintended host access.
这是一个基于MCP协议的执行控制平面,可为大语言模型客户端提供本地Shell访问、文件管理、浏览器自动化、临时文件共享链接以及远程机器控制能力。它自带DSH bundle清单,可以直接安装在DSH上,同时也原生支持ChatGPT开发者模式和其他任何兼容MCP协议的客户端,可通过Docker、预编译二进制、Python包、VS Code扩展等多种方式部署运行。
开发者可以用它给大模型开放一个受控的本地执行环境,让大模型直接帮你完成编译测试、代码调试、项目构建、日志排查等日常开发工作,也可以连接内网防火墙后的远程机器,让大模型控制这些设备完成任务。它适合需要让大模型获得真实执行能力的开发人员,也适合想要增强现有代理客户端本地操作能力的用户。
该项目依赖Python 3.11及以上版本,采用MIT许可证开源免费使用。它自带多重安全防护,包括工作区范围限制、命令超时、敏感信息过滤、审计日志等,但它开放了高权限能力,使用者需要遵循安全规则,建议在隔离容器或虚拟机中运行,不要把敏感权限开放给不受信任的模型。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:local-shell-mcp(fwerkor/local-shell-mcp)
仓库:https://github.com/fwerkor/local-shell-mcp
本站详情页:https://www.yhbd.top/plugins/fwerkor-local-shell-mcp/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 82 · 最近提交 2026-09-30 · 主语言 Python
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号(星标、许可证、更新活跃度、清单完整度)
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add 'github:fwerkor/local-shell-mcp#main'
把 fwerkor/local-shell-mcp 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
local-shell-mcp
A ChatGPT-ready MCP control plane for shell, files, browser automation, file links, and remote machines.
Documentation · Quickstart · Runtime choices · ChatGPT connector · DSH plugin · Tools · Releases
local-shell-mcp gives ChatGPT Developer Mode and other MCP clients controlled access to a real execution environment. It exposes a dedicated workspace with shell, persistent shell, filesystem, search, patch, Playwright, audit, durable logical sessions with optional Goal plans, public file links, and outbound remote-worker access. Git is handled through ordinary shell commands instead of a parallel wrapper API.
Runtime: Docker / VS Code extension / binary / Python / stdio
-> exposure: localhost, HTTPS proxy/tunnel, or stdio pipe
-> client: ChatGPT or another MCP client
-> controlled workspace at /workspace or configured root
-> optional remote workers connected over outbound HTTP(S)
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
esengine/DeepSeek-Reasonix
strukto-ai/mirage
chuspeeism/dashi-taskboard
Aisland-SJL/dsh-worktable
ccch1mneyyy/working-activity
zhoushoujianwork/easyeda-agent
pulseaiclub/phi
Ikalus1988/MisakaNet