Stop and remove a sandbox session container
AI agents call sandbox.stop to permanently remove resources in Dynamic — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Stopping and removing a sandbox container is irreversible; any in-progress work, ephemeral state, and the container itself are permanently destroyed. This matches the Destructive category. Severity is high because misuse could terminate active sandbox sessions and lose all unsaved work within them, affecting potentially multiple running processes or tools.
From the tool's definition 'Stop and remove a sandbox session container' — the word 'remove' indicates irreversible deletion of the container and its state.
Attacks that exploit this kind of access
Stop and remove a sandbox session container. It is categorised as a Destructive tool in the Dynamic MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dynamic MCP server in PolicyLayer and add a rule for sandbox.stop: 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 Dynamic. Nothing to install.
sandbox.stop is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the sandbox.stop 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.stop. 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.stop is provided by the Dynamic MCP server (mcpland/dynamic-mcp). 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 →