
Filesystem MCP Server
MCPMCP 官方参考实现:在授权目录白名单内读写、编辑、移动与搜索本地文件,支持通过 Roots 动态调整可访问目录,适合在桌面客户端里整理文档。
Filesystem MCP Server
Node.js server implementing Model Context Protocol (MCP) for filesystem operations.
Published on npm as @modelcontextprotocol/server-filesystem.
Features
- Read/write files
- Create/list/delete directories
- Move files/directories
- Search files
- Get file metadata
- Dynamic directory access control via Roots
Directory Access Control
The server uses a flexible directory access control system. Directories can be specified via command-line arguments or dynamically via Roots.
Method 1: Command-line Arguments
Specify Allowed directories when starting the server:
mcp-server-filesystem /path/to/dir1 /path/to/dir2
Method 2: MCP Roots (Recommended)
MCP clients that support Roots can dynamically update the Allowed directories.
Roots notified by Client to Server, completely replace any server-side Allowed directories when provided.
Important: If server starts without command-line arguments AND client doesn't support roots protocol (or provides empty roots), the server will throw an error during initialization.
This is the recommended method, as this enables runtime directory updates via roots/list_changed notifications without server restart, providing a more flexible and modern integration experience.
How It Works
The server's directory access control follows this flow:
-
Server Startup
- Server starts with directories from command-line arguments (if provided)
- If no arguments provided, server starts with empty allowed directories
-
Client Connection & Initialization
- Client connects and sends
initializerequest with capabilities - Server checks if client supports roots protocol (
capabilities.roots)
- Client connects and sends
-
Roots Protocol Handling (if client supports roots)
- On initialization: Server requests roots from client via
roots/list - Client responds with its configured roots
- Server replaces ALL allowed directories with client's roots
- On runtime updates: Client can send
notifications/roots/list_changed - Server requests updated roots and replaces allowed directories again
- On initialization: Server requests roots from client via
-
Fallback Behavior (if client doesn't support roots)
- Server continues using command-line directories only
- No dynamic updates possible
-
Access Control
- All filesystem operations are restricted to allowed directories
- Use
list_allowed_directoriestool to see current directories - Server requires at least ONE allowed directory to operate
Note: The server will only allow operations within directories specified either via args or via Roots.
API
Tools
-
read_text_file
- Read complete contents of a file as text
- Inputs:
path(string)head(number, optional): First N linestail(number, optional): Last N lines
- Always treats the file as UTF-8 text regardless of extension
- Cannot specify both
headandtailsimultaneously
-
read_media_file
- Read a file and return it as a base64-encoded content block with its MIME type
- Inputs:
path(string)
- Streams the file and returns base64 data with the corresponding MIME type. Image and
audio files are returned as
image/audiocontent; any other file type is returned as an embeddedresource(a valid MCP content block for arbitrary binary data)
-
read_multiple_files
- Read multiple files simultaneously
- Input:
paths(string[]) - Failed reads won't stop the entire operation
-
write_file
- Create new file or overwrite existing (exercise caution with this)
- Inputs:
path(string): File locationcontent(string): File content
-
edit_file
- Make selective edits using advanced pattern matching and formatting
- Features:
- Line-based and multi-line content matching
- Whitespace normalization with indentation preservation
- Multiple simultaneous edits with correct positioning
- Indentation style detection and preservation
- Git-style diff output with context
- Preview changes with dry run mode
- Inputs:
path(string): File to editedits(array): List of edit operationsoldText(string): Text to search for (can be substring)newText(string): Text to replace with
dryRun(boolean): Preview changes without applying (default: false)
- Returns detailed diff and match information for dry runs, otherwise applies changes
- Best Practice: Always use dryRun first to preview changes before applying them
-
create_directory
- Create new directory or ensure it exists
- Input:
path(string) - Creates parent directories if needed
- Succeeds silently if directory exists
-
list_directory
- List directory contents with [FILE] or [DIR] prefixes
- Input:
path(string)
-
list_directory_with_sizes
- List directory contents with [FILE] or [DIR] prefixes, including file sizes
- Inputs:
path(string): Directory path to listsortBy(string, optional): Sort entries by "name" or "size" (default: "name")
- Returns detailed listing with file sizes and summary statistics
- Shows total files, directories, and combined size
-
move_file
- Move or rename files and directories
- Inputs:
source(string)destination(string)
- Fails if destination exists
-
search_files
- Recursively search for files/directories that match or do not match patterns
- Inputs:
path(string): Starting directorypattern(string): Search patternexcludePatterns(string[]): Exclude any patterns.
- Glob-style pattern matching
- Returns full paths to matches
-
directory_tree
- Get recursive JSON tree structure of directory contents
- Inputs:
path(string): Starting directoryexcludePatterns(string[]): Exclude any patterns. Glob formats are supported.
- Returns:
- JSON array where each entry contains:
name(string): File/directory nametype('file'|'directory'): Entry typechildren(array): Present only for directories- Empty array for empty directories
- Omitted for files
- JSON array where each entry contains:
- Output is formatted with 2-space indentation for readability
-
get_file_info
- Get detailed file/directory metadata
- Input:
path(string) - Returns:
- Size
- Creation time
- Modified time
- Access time
- Type (file/directory)
- Permissions
-
list_allowed_directories
- List all directories the server is allowed to access
- No input required
- Returns:
- Directories that this server can read/write from
Tool annotations (MCP hints)
This server sets MCP ToolAnnotations on each tool so clients can:
- Distinguish read‑only tools from write‑capable tools.
- Understand which write operations are idempotent (safe to retry with the same arguments).
- Highlight operations that may be destructive (overwriting or heavily mutating data).
- Signal that a tool does not reach an open or external world (every filesystem tool sets
openWorldHint: false).
The mapping for filesystem tools is:
| Tool | readOnlyHint | idempotentHint | destructiveHint | Notes |
|---|---|---|---|---|
read_text_file | true | – | – | Pure read |
read_media_file | true | – | – | Pure read |
read_multiple_files | true | – | – | Pure read |
list_directory | true | – | – | Pure read |
list_directory_with_sizes | true | – | – | Pure read |
directory_tree | true | – | – | Pure read |
search_files | true | – | – | Pure read |
get_file_info | true | – | – | Pure read |
list_allowed_directories | true | – | – | Pure read |
create_directory | false | true | false | Re‑creating the same dir is a no‑op |
write_file | false | true | true | Overwrites existing files |
edit_file | false | false | true | Re‑applying edits can fail or double‑apply |
move_file | false | false | true | Deletes source file |
Note:
idempotentHintanddestructiveHintare meaningful only whenreadOnlyHintisfalse, as defined by the MCP spec. Every tool also setsopenWorldHint: false— this server only accesses the local filesystem within its allowed directories, never an open or external world.
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
Note: you can provide sandboxed directories to the server by mounting them to /projects. Adding the ro flag will make the directory readonly by the server.
Docker
Note: all directories must be mounted to /projects by default.
{
"mcpServers": {
"filesystem": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--mount", "type=bind,src=/Users/username/Desktop,dst=/projects/Desktop",
"--mount", "type=bind,src=/path/to/other/allowed/dir,dst=/projects/other/allowed/dir,ro",
"--mount", "type=bind,src=/path/to/file.txt,dst=/projects/path/to/file.txt",
"mcp/filesystem",
"/projects"
]
}
}
}
NPX
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/username/Desktop",
"/path/to/other/allowed/dir"
]
}
}
}
On Windows, use cmd /c to launch npx:
{
"mcpServers": {
"filesystem": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/username/Desktop",
"/path/to/other/allowed/dir"
]
}
}
}
Usage with VS Code
For quick installation, click the installation buttons below...
For manual installation, you can configure the MCP server using one of these methods:
Method 1: User Configuration (Recommended)
Add the configuration to your user-level MCP configuration file. Open the Command Palette (Ctrl + Shift + P) and run MCP: Open User Configuration. This will open your user mcp.json file where you can add the server configuration.
Method 2: Workspace Configuration
Alternatively, you can add the configuration to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.
For more details about MCP configuration in VS Code, see the official VS Code MCP documentation.
You can provide sandboxed directories to the server by mounting them to /projects. Adding the ro flag will make the directory readonly by the server.
Docker
Note: all directories must be mounted to /projects by default.
{
"servers": {
"filesystem": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--mount", "type=bind,src=${workspaceFolder},dst=/projects/workspace",
"mcp/filesystem",
"/projects"
]
}
}
}
NPX
{
"servers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"${workspaceFolder}"
]
}
}
}
On Windows, use:
{
"servers": {
"filesystem": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"@modelcontextprotocol/server-filesystem",
"${workspaceFolder}"
]
}
}
}
Build
Docker build:
docker build -t mcp/filesystem -f src/filesystem/Dockerfile .
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
相关资源

Awesome Claude Skills (Composio)
SkillClaude 技能精选索引,仓库内自带约 30 个实用技能(简历定制、内容调研写作、文件整理、会议分析等),另有 800 多个经 Composio 连接第三方应用的自动化技能,需接入 Rube MCP 并授权账号。
ComposioHQ/awesome-claude-skills76.6k
Google Docs, Sheets, Drive, Gmail & Calendar MCP Server
MCP一个服务同时读写 Google 文档、表格、云端硬盘、Gmail 和日历:起草与排版文档、处理批注、整理表格和图表、分拣邮件、安排日程。需要先在 Google Cloud 创建 OAuth 客户端并运行一次授权命令,本机需 Node.js。
a-bonus/google-docs-mcp664
Mole
CLImacOS 系统清理与维护命令行 mo:清理缓存和日志、彻底卸载应用、分析磁盘占用、清理项目构建产物、查看系统状态;删除类命令可先用 --dry-run 预览,磁盘分析与状态支持 JSON 输出。需要 macOS 12+。
tw93/Mole68.6k
Google Drive
PluginOpenAI 官方 Codex 插件,以 Google Drive 为统一入口,负责搜索、整理、共享和导出云盘文件。涉及 Docs、Sheets、Slides 与评论时交给对应子技能,完成摘要、编辑和新建。需在 Codex 中授权 Google 账号。
openai/plugins7.2k
textlint
CLI可插拔的自然语言检查工具,像检查代码一样按规则检查 Markdown 与纯文本稿件的用词、标点和术语一致性并自动修正,也能作为 MCP 服务运行。规则需另装,生态以日语、英语规则为主;需要 Node.js 20 以上。
textlint/textlint3.2k
lint-md
CLI检查并自动修复中文 Markdown 的排版问题,如中英文之间缺空格、中文语境误用半角标点、空链接等,适合写博客、知识库和技术文档时统一格式。命令行版 @lint-md/cli 由同一团队在 lint-md/cli 仓库维护,需要本机装有 Node.js。
lint-md/lint-md958