ClawCrate

Policy + evidence for everything your AI agent executes. 🦀 Kernel-native sandbox for agent commands & MCP servers — Landlock+seccomp (Linux), Seatbelt (macOS). Tamper-evident, offline-verifiable audit trail. No Docker, no root, one Rust binary. Agent-agnostic.

{
  "mcpServers": {
    "clawcrate": {
      "command": "cargo",
      "args": [
        "run",
        "--",
        "ClawCrate"
      ]
    }
  }
}

claude mcp add clawcrate cargo run -- ClawCrate

{
  "mcpServers": {
    "clawcrate": {
      "command": "cargo",
      "args": [
        "run",
        "--",
        "ClawCrate"
      ]
    }
  }
}