filesystem_sandbox
A safe MCP server for sandboxed filesystem operations (list, move, create directories, delete files) via pure Python, designed for Claude Desktop.
README
MCP Filesystem Sandbox
A simple, safe, Python MCP server that exposes filesystem operations (list files, move files, create directories, delete files) inside a single sandboxed directory.
The server is designed for learning and personal use with Claude Desktop via the Model Context Protocol (MCP).
Features
- Relative-path sandboxing (no access outside the allowed directory)
- No shell execution (pure Python filesystem APIs)
- Safe file-only deletion (directories cannot be deleted)
- Minimal, explicit tool surface
- Designed for use with Claude Desktop via MCP
Sandbox directory
This server operates inside one sandbox directory.
You must provide the sandbox path as the first argument when starting the server:
uv run server.py /absolute/path/to/sandbox
All filesystem operations are restricted to this directory. Paths passed to tools are always relative to the sandbox root.
Use "." to refer to the sandbox root itself.
Running the server
From the project directory:
uv run server.py /absolute/path/to/sandbox
The server will start and wait for MCP tool calls over stdio. No output is expected while it is running.
Using with Claude Desktop (MCP)
Example MCP configuration:
{
"mcpServers": {
"filesystem_sandbox": {
"command": "uv",
"args": [
"--directory",
"/path/to/project",
"run",
"server.py",
"/absolute/path/to/sandbox"
]
}
}
}
After updating the configuration, restart Claude Desktop.
Note: Depending on your system, you may need to use the full
path to the uv executable (for example /Users/you/.local/bin/uv)
instead of uv in the MCP configuration.
Safety notes
- All paths are resolved relative to the sandbox directory
- Absolute paths and directory traversal (
..) are blocked - Directories cannot be deleted
- No shell commands are executed
This server is intended for safe experimentation and learning.
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.