shutil-mcp
shutil-mcp
一个使用 aioshutil 提供异步 shell 工具的 MCP 服务器。
该项目为 AI 代理提供了一组文件系统工具,返回结构化 JSON 输出而非原始文本。这使得 AI 模型能够更精确、更直接地使用文件系统数据。
功能特性
异步操作:利用
aioshutil和线程执行器实现非阻塞文件系统任务。JSON 输出:所有工具返回压缩后的 JSON,针对 AI 代理进行了优化。
Jail 支持:将文件系统访问限制在特定目录树内以增强安全性。
验证与完整性:
mv和cp在取消链接或完成操作前验证目标数据,防止部分失败时造成数据丢失。可逆变更与撤销:
chmod和chown返回先前的模式和所有权,便于立即撤销/重做,并在失败时自动回滚。软删除与恢复:
rm支持trash=True软删除,并配有对应的restore工具。Zip-Slip 防护:
unpack_archive验证所有归档成员路径,防止目录遍历 / zip-slip 攻击。详细元数据:
ls和stat等工具提供全面的信息(大小、mtime、模式、所有者等)。HTTP 传输支持:内置对 SSE 和 Streamable HTTP 传输的支持。
Related MCP server: File Manager MCP Server
可用工具
ls:列出目录内容及详细元数据。cp:递归复制文件或目录并进行验证。mv:移动/重命名文件或目录,并在删除前进行安全验证。rm:删除文件或目录(支持trash=True软删除)。restore:从回收站恢复文件或目录。chmod:更改文件/目录权限,支持回滚并返回先前模式。chown:更改文件/目录所有权,支持回滚并返回先前所有者。disk_usage:获取路径的磁盘使用统计信息。which:查找可执行文件的路径。cat:读取文件内容,可选择限制在特定行范围内。glob:查找匹配 glob 模式的文件。grep:使用正则表达式搜索文件内容。tree:以嵌套 JSON 形式获取递归目录树。make_archive:创建归档文件(zip、tar 等),带覆盖保护。unpack_archive:安全解压归档文件,带 zip-slip 防护。get_archive_formats:列出支持的归档格式。
安装
pip install shutil-mcp使用方法
使用 stdio 传输运行
shutil-mcp --transport stdio使用 jail 限制运行
shutil-mcp --transport stdio --jail /path/to/projects作为 SSE 服务器运行
shutil-mcp --transport sse --jail /path/to/projects --port 8000开发
详细开发说明请参阅 DEVELOPMENT.md。
许可证
MIT
This server cannot be installed
Maintenance
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables secure filesystem operations with directory sandboxing and optional read-only mode. Supports file reading/writing, directory management, file searching, and text operations while restricting access to specified directories.12
- FlicenseNot gradedqualityDmaintenanceProvides secure file system operations for AI assistants including directory listing, file reading/writing, deletion, searching, and copying. Features safety controls like path validation, permission checks, and file size limits.
- AlicenseNot gradedqualityCmaintenanceProvides secure, sandboxed file system access for AI assistants to read, write, and manage project files with controlled command execution capabilities, all confined to a designated workspace directory.MIT
- FlicenseNot gradedqualityDmaintenanceProvides secure file read and write operations within a sandboxed directory, allowing AI assistants to safely create, modify, and access files without risk of accessing the broader file system.
Related MCP Connectors
Securely search and manage workspace context files for AI agents and teams.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Project management MCP for AI agents with safe task reads and writes.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cwt/shutil-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server