shutil-mcp
Provides asynchronous file system operations (ls, cp, mv, etc.) with structured JSON output and optional jail restriction for AI agents.
README
shutil-mcp
An MCP server providing asynchronous shell utilities using aioshutil.
This project offers a set of file system tools designed for AI agents, returning structured JSON output instead of raw text. This allows for more precise and direct consumption of file system data by AI models.
Features
- Asynchronous Operations: Leverages
aioshutilfor non-blocking file system tasks. - JSON Output: All tools return minified JSON, optimized for AI agents.
- Jail Support: Restrict file system access to a specific directory tree for security.
- Detailed Metadata: Tools like
lsprovide comprehensive information (size, mtime, mode, owner, etc.). - HTTP Transport Support: Includes built-in support for SSE and Streamable HTTP transports.
Available Tools
ls: List directory contents with detailed metadata.cp: Copy files or directories recursively.mv: Move/rename files or directories.rm: Remove files or directories recursively.chmod: Change file/directory permissions.chown: Change file/directory ownership.disk_usage: Get disk usage statistics for a path.which: Find the path to an executable.cat: Read file content, optionally limited to a specific line range.make_archive: Create archive files (zip, tar, etc.).unpack_archive: Unpack archive files.get_archive_formats: List supported archive formats.
Installation
pip install shutil-mcp
Usage
Run with stdio transport
shutil-mcp --transport stdio
Run with jail restriction
shutil-mcp --transport stdio --jail /path/to/projects
Run as SSE server
shutil-mcp --transport sse --jail /path/to/projects --port 8000
Development
See @DEVELOPMENT.md for detailed development instructions.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.