Get detailed information about a specific sandbox including full configuration.
AI agents call sandbox_inspect to retrieve information from Microsandbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries sandbox configuration and metadata without modifying, deleting, or executing any code. It is analogous to a 'get' or 'describe' operation. While it exposes configuration details (which could reveal sensitive information if misused), the action itself is non-destructive and side-effect-free, placing it squarely in the Read category.
From the tool's definition Tool is named 'sandbox_inspect' and description states 'Get detailed information about a specific sandbox including full configuration.' The verb 'Get' and the absence of any modification, deletion, or code execution language indicate a read-only operation.
Documented attack patterns abuse exactly the kind of access sandbox_inspect 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_inspect:
{
"version": "1",
"default": "deny",
"tools": {
"sandbox_inspect": {}
}
}sandbox_inspect is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get detailed information about a specific sandbox including full configuration. It is categorised as a Read tool in the Microsandbox MCP Server, which means it retrieves data without modifying state.
Register the Microsandbox MCP server in PolicyLayer and add a rule for sandbox_inspect: 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_inspect is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sandbox_inspect 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_inspect. 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_inspect 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.