What is Mcp Filesystem?
It is a secure MCP server that gives AI models controlled access to files and directories, preventing unauthorized path traversal by only permitting operations inside explicitly allowed directories.
@gabrielmaialva33
基本信息
A secure Model Context Protocol (MCP) server providing filesystem access within predefined directories
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-filesystem": {
"command": "npx",
"args": [
"@gabrielmaialva33/mcp-filesystem",
"/path/to/allowed/directory"
]
}
}
}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。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Mcp Filesystem is a secure Model Context Protocol (MCP) server that provides controlled filesystem access for AI models. It enforces strict path validation and only allows operations within predefined directories, making it suitable for applications needing safe file read/write capabilities.
Install via npm (npx @gabrielmaialva33/mcp-filesystem) or clone the repository and build locally. Run the server by specifying allowed directory paths as arguments (e.g., mcp-filesystem /path/to/allowed/dir). Optionally use a JSON configuration file with --config=config.json. Integrate with Claude Desktop by adding a filesystem entry in claude_desktop_config.json.
It is a secure MCP server that gives AI models controlled access to files and directories, preventing unauthorized path traversal by only permitting operations inside explicitly allowed directories.
You can install it globally via npm (`npm install -g @gabrielmaialva33/mcp-filesystem`) or use npx without installation. Run the server by passing one or more directory paths as arguments. A configuration file can be created with `--create-config=config.json`.
It offers file operations (read, write, edit, move), directory operations (create, list, tree, search), file metadata retrieval, secure command execution, and HTTP requests (coming in v1.2.0). Performance metrics and logging are available from v0.3.0.
Add an entry to `claude_desktop_config.json` under `mcpServers` with the command `mcp-filesystem` (or `npx @gabrielmaialva33/mcp-filesystem`) and list allowed directories as arguments. Docker usage is also supported with volume mounts.
You can set allowed directories, log level, log file path, server name/version, caching settings (enabled, maxSize, ttlMs), metrics reporting interval, and security constraints like max file size (default 10 MB) and symlink handling. See the example `config.json` in the README.
MCP server for working with PDF files
A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
📄 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.
Blazing-fast, asynchronous MCP server for seamless filesystem operations.
评论