sandbox_install · MCP Multi-Language Sandbox MCP

WHAT IT DOES

What sandbox_install does on MCP Multi-Language Sandbox

AI agents invoke sandbox_install to trigger actions in MCP Multi-Language Sandbox. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why sandbox_install needs a policy

Package installation is more than a write operation: it fetches and runs arbitrary third-party code (build scripts, post-install hooks), which constitutes execution. Within a Docker-isolated sandbox the blast radius is partially contained, but a malicious or misconfigured package could compromise the session, exfiltrate data, or serve as a stepping stone.

From the tool's definition 'Install packages in a sandbox session' — installing packages executes external code/scripts (setup.py, build scripts, post-install hooks) and modifies the sandbox environment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandbox_install Rate-limited

sandbox_install stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandbox_install": {
      "limits": [
        {
          "counter": "sandbox_install_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Multi-Language Sandbox, so you can run agents against it safely.

FAQ

Questions about sandbox_install

What does the sandbox_install tool do? +

Install packages in a sandbox session. Uses caching for fast repeated installs. It is categorised as a Execute tool in the MCP Multi-Language Sandbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sandbox_install? +

Register the MCP Multi-Language Sandbox MCP server in PolicyLayer and add a rule for sandbox_install: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Multi-Language Sandbox. Nothing to install.

What risk level is sandbox_install? +

sandbox_install is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sandbox_install? +

Yes. Add a rate_limit block to the sandbox_install rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block sandbox_install completely? +

Set action: deny in the PolicyLayer policy for sandbox_install. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides sandbox_install? +

sandbox_install is provided by the MCP Multi-Language Sandbox MCP server (pit-cl/mcp-multilang-sandbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.