box
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support pla
Ranked by AgentPick Score, our data score from public GitHub activity. Description is the project's own.
Topics: agentic-ai, agents, ai, ai-agents, ai-safety, containment, egress, harness, linux, llm, macos, mcp
Starter prompt
Connect the box MCP server to my agent with the narrowest permissions possible, then do [task] and tell me which tool calls you made.
More in MCP servers
FastMCP →
🚀 The fast, Pythonic way to build MCP servers and clients.
Chrome DevTools MCP →
Chrome DevTools for coding agents
Codebase Memory MCP →
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average r…
Composio →
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to …
MCP Python SDK →
The official Python SDK for Model Context Protocol servers and clients
MCP Toolbox for Databases →
MCP Toolbox for Databases is an open source MCP server for databases.
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.