Filesystem MCP Server

@ai-yliu

代码仓库

基本信息

分类

文件与存储

传输方式

stdio

作者

ai-yliu

关于 Filesystem MCP Server

A Model Context Protocol (MCP) server that provides filesystem operations for Claude AI

#filesystem #mcp #server #claude-ai

Filesystem MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "filesystem-mcp-server-ai-yliu": {
      "command": "node",
      "args": [
        "build/index.js",
        "/path/to/allowed/dir1",
        "/path/to/allowed/dir2"
      ]
    }
  }
}

Filesystem MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Filesystem MCP Server?

Filesystem MCP Server is a Model Context Protocol server that provides filesystem operations for Claude AI. It allows AI models to read, write, list, move, search, and get metadata about files and directories within explicitly allowed directories.

How to use Filesystem MCP Server?

Install dependencies with npm install, build with npm run build, then run the server specifying one or more allowed directories as command‑line arguments (e.g., node build/index.js /path/to/allowed/dir1 /path/to/allowed/dir2). Configure it in your MCP client’s JSON configuration file.

Key features of Filesystem MCP Server

Read complete file contents with UTF‑8 encoding
Write new files or overwrite existing ones
Create directories (including parent directories)
List directory contents with [FILE] or [DIR] prefixes
Move or rename files and directories
Recursively search for files/directories with case‑insensitive matching
Get detailed file metadata (size, times, permissions)
List all directories the server is allowed to access

Use cases of Filesystem MCP Server

AI assistants reading local text files to answer user questions
Writing configuration files or scripts from AI‑generated content
Browsing directory structures to understand project layouts
Searching for files by name across a codebase
Moving or organizing files within approved directories

常见问题

What filesystem operations does this server support?

It supports reading, writing, creating directories, listing, moving, searching, and getting file metadata. Specific tools include `read_file`, `read_multiple_files`, `write_file`, `create_directory`, `list_directory`, `move_file`, `search_files`, `get_file_info`, and `list_allowed_directories`.

How does the server enforce security?

The server only allows operations within directories specified via command‑line arguments. No operations are permitted outside those allowed directories.

What are the runtime requirements?

Node.js is required. Install dependencies with `npm install` and build with `npm run build` before running.

Can the server read multiple files at once?

Yes, the `read_multiple_files` tool accepts an array of paths and reads them simultaneously. Failed reads do not stop the entire operation.

How do I configure the server with my MCP client?

Add an entry to your MCP configuration file that specifies the command (`node`), the path to the built `index.js`, and the allowed directory paths. Optionally set `disabled` and `autoApprove`.

文件与存储分类下的更多 MCP 服务器

MCP File System Server

MarcusJellinghaus

MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.

DeviceLink

Jayanka Sampath

DeviceLink lets you share folders from your computer with AI assistants, securely and in real-time. Nothing is uploaded. Your files stay on your machine, and are only accessible while the device sharing them is connected

PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

shtse8

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810