Executes a terminal command in the specified sandbox. Parameters: sandbox_id (string), command (string). Returns stdout, stderr, exit_code.
AI agents invoke execute_terminal_command to trigger actions in MCP 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.
This tool permits execution of arbitrary shell commands whose side effects are entirely dependent on the argument provided. While sandboxed (mitigating some risk), a malicious or confused agent could execute destructive commands (rm -rf, data exfiltration), install malware, or consume resources. The blast radius is high because terminal commands can affect the sandbox filesystem, network, and processes.
From the tool's definition Tool name 'execute_terminal_command' and description states it 'Executes a terminal command in the specified sandbox' with arbitrary command parameter.
Documented attack patterns abuse exactly the kind of access execute_terminal_command gives an agent:
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 execute_terminal_command:
{
"version": "1",
"default": "deny",
"tools": {
"execute_terminal_command": {
"limits": [
{
"counter": "execute_terminal_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_terminal_command 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.
Free to start. No card required.
Executes a terminal command in the specified sandbox. Parameters: sandbox_id (string), command (string). Returns stdout, stderr, exit_code. 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.
Register the MCP Sandbox MCP server in PolicyLayer and add a rule for execute_terminal_command: 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.
execute_terminal_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_terminal_command 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.
Set action: deny in the PolicyLayer policy for execute_terminal_command. 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.
execute_terminal_command 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.
Start from MCP Sandbox, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 MCP Sandbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.