runbox_create_sandbox
Create a new python+nodejs Runbox code sandbox linux debian to write code files and run it
This record as markdown: /tools/11cafe-website-publisher-mcp/runbox-create-sandbox.md
What runbox_create_sandbox does on Runbox Website Builder MCP
AI agents invoke runbox_create_sandbox to trigger actions in Runbox Website Builder MCP. 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.
Why runbox_create_sandbox is rated High
This tool provisions a live Linux Debian sandbox environment capable of executing Python and Node.js code. Spinning up an execution environment is itself an Execute-category action with high blast radius, as it enables arbitrary code execution in a real OS context. Though 'create' suggests Write, the primary purpose and risk is enabling arbitrary code execution.
From the tool's definition Create a new python+nodejs Runbox code sandbox linux debian to write code files and run it
Attacks that exploit this kind of access
The rule that runs runbox_create_sandbox safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Runbox Website Builder MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For runbox_create_sandbox, this is the rule to start with:
runbox_create_sandbox 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Runbox Website Builder MCP, apply this rule, and every runbox_create_sandbox call is checked against it from then on.
Questions about runbox_create_sandbox
Create a new python+nodejs Runbox code sandbox linux debian to write code files and run it. It is categorised as a Execute tool in the Runbox Website Builder MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Runbox Website Builder MCP server in PolicyLayer and add a rule for runbox_create_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 Runbox Website Builder MCP. Nothing to install.
runbox_create_sandbox 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 runbox_create_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.
Set action: deny in the PolicyLayer policy for runbox_create_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.
runbox_create_sandbox is provided by the Runbox Website Builder MCP server (11cafe/website-publisher-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Runbox Website Builder, and thousands of servers like it.
Across the catalogue