Execute a shell command or script string inside a running sandbox.
AI agents invoke sandbox_shell to trigger actions in Microsandbox. 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 runs arbitrary shell commands within a sandbox environment, which is a quintessential Execute category action. While the sandbox provides containment (mitigating some risk vs. local execution), an AI agent could still misuse this to run destructive commands (rm -rf), exfiltrate data, or perform unauthorized operations within the sandbox.
From the tool's definition Tool description states 'Execute a shell command or script string inside a running sandbox.' The verb 'Execute' combined with acceptance of arbitrary 'shell command or script string' indicates code execution capability.
Documented attack patterns abuse exactly the kind of access sandbox_shell gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Microsandbox, and nothing reaches the server without passing your rules. This is the rule we recommend for sandbox_shell:
{
"version": "1",
"default": "deny",
"tools": {
"sandbox_shell": {
"limits": [
{
"counter": "sandbox_shell_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}sandbox_shell 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.
Execute a shell command or script string inside a running sandbox. It is categorised as a Execute tool in the Microsandbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Microsandbox MCP server in PolicyLayer and add a rule for sandbox_shell: 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 Microsandbox. Nothing to install.
sandbox_shell 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 sandbox_shell 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 sandbox_shell. 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.
sandbox_shell is provided by the Microsandbox MCP server (superradcompany/microsandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Microsandbox, 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.
19 Microsandbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.