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

Filesystem MCP

作者:j0hanz版本 2.19.2i★ –i在你的电脑上运行
注册名称io.github.j0hanz/filesystem-mcp

安装

概览

作者提供的说明(英文原文)

Filesystem MCP server for AI assistants.

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: FS_ALLOWED_DIRS, FS_READ_ONLY_DIRS

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": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@j0hanz/filesystem-mcp"
      ],
      "env": {
        "FS_ALLOWED_DIRS": "your-value",
        "FS_READ_ONLY_DIRS": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add filesystem --env FS_ALLOWED_DIRS=your-value --env FS_READ_ONLY_DIRS=your-value -- npx -y @j0hanz/filesystem-mcp

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": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@j0hanz/filesystem-mcp"
      ],
      "env": {
        "FS_ALLOWED_DIRS": "your-value",
        "FS_READ_ONLY_DIRS": "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": {
    "filesystem": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@j0hanz/filesystem-mcp"
      ],
      "env": {
        "FS_ALLOWED_DIRS": "your-value",
        "FS_READ_ONLY_DIRS": "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

  • FS_ALLOWED_DIRS env
    Allowed directories; ':'-separated on Unix, ';'-separated on Windows. Alternative to positional arguments.
  • FS_READ_ONLY_DIRS env
    Read-only directories; ':'-separated on Unix, ';'-separated on Windows. Writes, moves, and deletes under them are refused.

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 j0hanz 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 18349 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 18349 个服务器的 100% 更新
  • 基础检查结果等于或优于此分类中其他 18349 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

Filesystem MCP 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(2.19.2)于今天进入注册中心。

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, Docker。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, arr-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

arr-mcp

作者:bardesss

One server, 40 tools, the whole media stack: *arrs, Jellyfin, Plex, Seerr, Cleanuparr, downloaders

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。

Filesystem MCP

Let your AI assistant work with your files, safely.

Read, search, edit, and patch files in the folders you choose.

Secret files stay hidden, and risky changes wait for your OK.

Real sessions with a real model, except the web client demo. The apply? prompt comes from the example gatekeeper client, not the server.

Undo skips a file you edited since, so your edit stays

Rename across a repo, reviewed as one diff, with dist/ and .env untouched

Bring back a deleted folder that git can't restore

Secret files stay hidden, and overwrites wait for your OK

Move files into an archive, then undo a move that overwrote one

Review different edits to three files as one diff before they are written

A patch that no longer fits changes nothing

Find a crash in a 14 MB log without reading all of it

What is this?

Model Context Protocol (MCP) is how AI apps such as Claude, GitHub Copilot in VS Code, and Cursor connect to tools. Filesystem MCP is an MCP server: a small program that runs on your computer and gives the AI 14 tools for working with files. You choose which folders it can use, and everything outside them is off limits.

Once it is connected, you can ask things like:

  • _"Find every TODO in this repo and group them by file."_
  • _"Rename getUser to fetchUser in all .ts files. Show me the diff first."_
  • _"What changed between config.dev.json and config.prod.json?"_
  • _"Read the last 50 lines of server.log and explain the error."_
  • _"Move the old screenshots into archive/2025/."_

Why Filesystem MCP?

  • It is safe by default. The AI can use only the folders you allow, and .env files, private keys, and cloud credentials are blocked. The server asks you before the AI deletes a non-empty folder, opens a folder you did not allow, or writes over a file with create or move. These questions need a client that can show them. If yours cannot, the server refuses each of those actions instead of asking. Only create and copies can skip the question, because overwrite: true replaces a file without asking, on any client. undo can usually restore a file that create or a copy replaced. Edits made with edit, patch, and replace_text apply without asking, but the AI can show you the diff first with dryRun. If the AI should never change anything, --read-only removes every tool that writes.
  • Search and editing are made for code. The AI can search inside files like grep, with a regex engine (RE2) that cannot hang, and by default the server skips .gitignored files and folders like node_modules. Edits are exact-match replacements that return an error when the text does not match, and you can preview them as a diff first.
  • It saves the AI's context. The AI can read many files in one call or only the lines it needs, and it can check a file's size and token estimate before reading it.
  • It works with any MCP client, over stdio or HTTP, on macOS, Linux, and Windows. You can install it with npx, Docker, or a one-click Claude Desktop extension, or build your own client on it.
  • It is private. It runs on your machine, has no telemetry, and makes no network calls.
Compared with the reference server

How this server differs from the official @modelcontextprotocol/server-filesystem, checked against its README on 2026-11-05:

CapabilityFilesystem MCPReference server
Search inside filessearch_text: literal text or RE2 regexNone; search_files matches names only
Secret files.env, keys, and credentials blocked by defaultNot blocked
Overwriting a filecreate asks first; overwrite: true does not askwrite_file overwrites without asking
Delete filesdelete; asks before deleting a non-empty folderNone
Undo a changeundo reverts recent changes; skips files edited sinceNone
.gitignoreRespected by listing and search toolsNot supported
Read-only mode--read-only removes every tool that writes--read-only removes every tool that writes
Per-folder read-only--read-only-root guards chosen foldersRun a second server with --read-only
Apply a unified diffpatchNone
Compare two filesdiffNone
Replace across many filesreplace_text over a folder or globNone
Watch filesSubscribe to a file and get change notificationsNone
Transportstdio, or Streamable HTTP with --portstdio

Quick start

[!NOTE]

You need Node.js 24 or later. Check with node --version.

  1. Add the server to your AI app. Pick yours below.
  2. Replace /path/to/project with the folder the AI may use. You can list several folders.
  3. Restart the app and ask: _"Which folders can you access?"_

[!TIP]

VS Code currently shares the folders you have open with the server, so the

one-click VS Code install works without a path. In other apps, or over HTTP,

put the folder in args. If the AI says it has no folders, that is the fix.

VS Code

Click Install in VS Code above, or add this to .vscode/mcp.json:

{

"servers": { "filesystem": { "command": "npx", "args": ["-y", "@j0hanz/filesystem-mcp@latest", "/path/to/project"] } } }

Or from a terminal:

code --add-mcp '{"name":"filesystem","command":"npx","args":["-y","@j0hanz/filesystem-mcp@latest","/path/to/project"]}'

Cursor

Click Install in Cursor above, then add your folder to args. Or add this to .cursor/mcp.json in your project, or ~/.cursor/mcp.json for all projects:

{

"mcpServers": { "filesystem": { "command": "npx", "args": ["-y", "@j0hanz/fil

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx