PulseAugur
实时 23:47:36

Hatch sandbox secures MCP servers with capability-based manifests

Hatch is a new capability-based sandbox designed for MCP (Model Context Protocol) servers, operating on Linux and macOS systems. It utilizes a signed TOML manifest to define server permissions, including network access, file system operations, and subprocess execution rules. Hatch enforces these rules through a combination of Linux namespaces, cgroups, and iptables, or sandbox-exec and PF on macOS, with additional network filtering for enhanced security. AI

影响 Provides enhanced security for AI model context protocols, potentially improving the safety of AI deployments.

排序理由 The article describes a new software tool for securing specific server protocols.

在 dev.to — MCP tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

报道来源 [1]

  1. dev.to — MCP tag TIER_1 English(EN) · Irfan ·

    Introducing hatch - a capability-based sandbox for MCP

    <p><a href="https://github.com/malwarebo/hatch" rel="noopener noreferrer">Github repo</a></p> <p>Hatch is a capability-based sandbox for MCP (Model Context Protocol) servers on Linux and macOS. Each server runs under a signed TOML manifest that declares its network destinations, …