Creates a new Python sandbox and returns its ID for subsequent operations. Optional parameter: name (string) - Custom name for the sandbox
AI agents use create_sandbox to create or update resources in MCP Sandbox — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Sandbox environment.
This tool creates a new sandbox resource that is reversible and does not execute arbitrary code, delete data, or trigger financial transactions. While the sandbox itself can be used to execute code via sibling tools, this particular tool only instantiates the container environment. The creation of isolated computational resources represents a Write operation (resource creation).
From the tool's definition Tool 'creates a new Python sandbox' and 'returns its ID for subsequent operations.' The description explicitly states it creates a new resource (sandbox environment) that can be used for subsequent operations.
Documented attack patterns abuse exactly the kind of access create_sandbox gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Sandbox, and nothing reaches the server without passing your rules. This is the rule we recommend for create_sandbox:
{
"version": "1",
"default": "deny",
"tools": {
"create_sandbox": {
"limits": [
{
"counter": "create_sandbox_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_sandbox stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Creates a new Python sandbox and returns its ID for subsequent operations. Optional parameter: name (string) - Custom name for the sandbox. It is categorised as a Write tool in the MCP Sandbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Sandbox MCP server in PolicyLayer and add a rule for 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 MCP Sandbox. Nothing to install.
create_sandbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the 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 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.
create_sandbox is provided by the MCP Sandbox MCP server (johanli233/mcp-sandbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Sandbox, 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.
7 MCP Sandbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.