Saves the container state to a persistent container
AI agents use save_container_state to create or update resources in Sandbox MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sandbox MCP Server environment.
Saving container state is a reversible operation that persists data. It modifies the system by storing a snapshot but does not destroy anything or execute arbitrary commands.
From the tool's definition Tool description states it 'Saves the container state to a persistent container' — this is a create/modify operation that writes state persistently but does not delete or irreversibly alter existing data.
Documented attack patterns abuse exactly the kind of access save_container_state gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sandbox MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for save_container_state:
{
"version": "1",
"default": "deny",
"tools": {
"save_container_state": {
"limits": [
{
"counter": "save_container_state_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} save_container_state 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.
Saves the container state to a persistent container. It is categorised as a Write tool in the Sandbox MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sandbox MCP Server MCP server in PolicyLayer and add a rule for save_container_state: 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 Sandbox MCP Server. Nothing to install.
save_container_state 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 save_container_state 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 save_container_state. 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.
save_container_state is provided by the Sandbox MCP Server MCP server (tsuchijo/sandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sandbox MCP Server, 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.
6 Sandbox MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.