Filesystem MCP Server
@MCP-Mirror
关于 Filesystem MCP Server
Mirror of
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ai-yliu_filesystem-mcp-server": {
"command": "node",
"args": [
"build/index.js",
"/path/to/allowed/dir1",
"/path/to/allowed/dir2"
]
}
}
}工具
未检测到工具
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 an AI assistant to read, write, move, search, and list files and directories, but only within directories explicitly allowed by the user.
How to use Filesystem MCP Server?
Clone the repository, run npm install and npm run build, then start the server with one or more allowed directories as arguments: node build/index.js /path/to/allowed/dir1 /path/to/allowed/dir2. Add the server to your MCP configuration file with the appropriate command and args. No additional configuration keys are required.
Key features of Filesystem MCP Server
- Read complete file contents with UTF-8 encoding
- Read multiple files simultaneously (partial failure allowed)
- 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 (fails if destination exists)
- Recursively search files/directories with case‑insensitive matching
- Retrieve detailed file metadata (size, times, type, permissions)
- List all directories the server can access
Use cases of Filesystem MCP Server
- Allow Claude AI to read and summarize documents from a safe sandbox folder
- Let an assistant write notes or configuration files into a controlled workspace
- Enable an AI to search for specific files across a project directory
- Provide AI with directory structure information for context‑aware responses
- Give an AI the ability to organize files (move/rename) within allowed bounds
FAQ from Filesystem MCP Server
Which directories can the server access?
Only directories passed as command‑line arguments when starting the server. Operations outside these directories are denied.
What dependencies or runtime are required?
Node.js and npm are required. After cloning, run npm install and npm run build to compile the server.
Where does file data live?
All file operations happen on the local filesystem. No data is sent to external services.
What transport does the server use?
The server communicates via standard input/output (stdin/stdout) following the Model Context Protocol. No network transport is involved.
How does authentication or auto‑approval work?
The server does not define any auto‑approve tools (the autoApprove array is empty by default). Each tool invocation must be explicitly approved by the user through the MCP client.
文件与存储 分类下的更多 MCP 服务器
Bulk Filesystem Operations MCP Server
strawgateMCP Server for reading many files at the same time

Google Drive
modelcontextprotocolModel Context Protocol Servers
Sample S3 Model Context Protocol Server
aws-samplesGoogle Drive MCP Server
hxie-pallasA google drive mcp servers based on Python
S3 MCP Server
samuraikunMCP server to integrate AWS S3 and LLM
评论