install_package_in_sandbox

THE RISK

High Risk

Why install_package_in_sandbox needs a policy

Installing a package triggers execution of a package manager and potentially arbitrary setup scripts (setup.py, post-install hooks). While confined to a sandbox/Docker container, a malicious or typo-squatted package could execute harmful code during installation. This is more than a Write (it runs code), making Execute the correct category.

From the tool's definition 'Installs a Python package in the specified sandbox' — installing a package executes package manager commands (e.g., pip install) inside the container, which runs external code and modifies the environment

Documented attack patterns abuse exactly the kind of access install_package_in_sandbox gives an agent:

POLICY

How to control install_package_in_sandbox

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Sandbox, and nothing reaches the server without passing your rules. This is the rule we recommend for install_package_in_sandbox:

policy.json

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

install_package_in_sandbox 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.

Create a free account and register MCP Sandbox — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Sandbox tools

Execute execute_python_code Executes Python code in a sandbox and returns results with links to generated files. Param Execute execute_terminal_command Executes a terminal command in the specified sandbox. Parameters: sandbox_id (string), com Write create_sandbox Creates a new Python sandbox and returns its ID for subsequent operations. Optional parame Write upload_file_to_sandbox Uploads a local file to the specified sandbox. Parameters: sandbox_id (string), local_file Read check_package_installation_status Checks the installation status of a package in a sandbox. Parameters: sandbox_id (string), Read list_sandboxes Lists all existing Python sandboxes and their status. Each item also includes installed Py

All 7 MCP Sandbox tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Sandbox → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about install_package_in_sandbox

What does the install_package_in_sandbox tool do? +

Installs a Python package in the specified sandbox. Parameters: sandbox_id (string), package_name (string). It is categorised as a Execute tool in the MCP 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 install_package_in_sandbox? +

Register the MCP Sandbox MCP server in PolicyLayer and add a rule for install_package_in_sandbox: 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 Sandbox. Nothing to install.

What risk level is install_package_in_sandbox? +

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

Can I rate-limit install_package_in_sandbox? +

Yes. Add a rate_limit block to the install_package_in_sandbox 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 install_package_in_sandbox completely? +

Set action: deny in the PolicyLayer policy for install_package_in_sandbox. 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 install_package_in_sandbox? +

install_package_in_sandbox is provided by the MCP Sandbox MCP server (johanli233/mcp-sandbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Sandbox tool call.

Start from MCP Sandbox, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →