kill_sandbox

Kill a sandbox

Server E2b yukkit/e2b-mcp-server
Category Destructive
Risk class Critical
Parameters 00 required

What kill_sandbox does on E2b

AI agents call kill_sandbox to permanently remove resources in E2b — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Why kill_sandbox needs a policy

Killing a sandbox permanently terminates the isolated execution environment. Any in-memory state, running processes, and unsaved data are lost. This cannot be undone, making it Destructive. The blast radius is high because it can abruptly terminate ongoing workloads and destroy ephemeral data.

From the tool's definition 'Kill a sandbox' — terminating a sandbox is an irreversible action that destroys the running environment and any unsaved state within it.

Questions about kill_sandbox

What does the kill_sandbox tool do? +

Kill a sandbox. It is categorised as a Destructive tool in the E2b MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on kill_sandbox? +

Register the E2b MCP server in PolicyLayer and add a rule for kill_sandbox: 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 E2b. Nothing to install.

What risk level is kill_sandbox? +

kill_sandbox is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit kill_sandbox? +

Yes. Add a rate_limit block to the kill_sandbox 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.

How do I block kill_sandbox completely? +

Set action: deny in the PolicyLayer policy for kill_sandbox. 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.

What MCP server provides kill_sandbox? +

kill_sandbox is provided by the E2b MCP server (yukkit/e2b-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.