Get stats and status of the sandbox system.
AI agents call sandbox_inspect to retrieve information from MCP Multi-Language Sandbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only operations to query the state of the sandbox infrastructure. It retrieves diagnostic and statistical data with no side effects, fitting the Read category. Severity is low because inspecting sandbox stats poses minimal risk even if accessed by an untrusted agent — the information disclosed is non-sensitive operational metadata.
From the tool's definition Tool name is 'sandbox_inspect' and description states 'Get stats and status of the sandbox system' — purely retrieves information about system status without modifying or executing code.
Attacks that exploit this kind of access
Get stats and status of the sandbox system. It is categorised as a Read tool in the MCP Multi-Language Sandbox MCP Server, which means it retrieves data without modifying state.
Register the MCP Multi-Language Sandbox 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 MCP Multi-Language Sandbox. 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 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →