sandbox_config · Yaver MCP: Risk & Policy

WHAT IT DOES

What sandbox_config does on Yaver

AI agents use sandbox_config to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.

PARAMETERS

Parameter	Type	Required	Description
`cpu_limit`	string	—	CPU limit (e.g. '2.0')
`read_only`	boolean	—	Read-only root filesystem (writes only to /workspace, /tmp)
`memory_limit`	string	—	Memory limit (e.g. '4g')
`network_mode`	string	—	Network mode: 'host', 'bridge', or 'none'
`containerize_host`	boolean	—	Run host tasks in Docker containers
`containerize_guests`	boolean	—	Run guest tasks in Docker containers

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why sandbox_config needs a policy

An AI agent can call sandbox_config faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandbox_config Rate-limited

sandbox_config 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandbox_config": {
      "limits": [
        {
          "counter": "sandbox_config_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Yaver, so you can run agents against it safely.

FAQ

Questions about sandbox_config

What does the sandbox_config tool do? +

Enable/disable container isolation for guest or host tasks. Configure resource limits and network mode. Changes are persisted to config file. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does sandbox_config accept? +

sandbox_config accepts 6 parameters: cpu_limit, read_only, memory_limit, network_mode, containerize_host, containerize_guests. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on sandbox_config? +

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

What risk level is sandbox_config? +

sandbox_config is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sandbox_config? +

Yes. Add a rate_limit block to the sandbox_config 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 sandbox_config completely? +

Set action: deny in the PolicyLayer policy for sandbox_config. 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 sandbox_config? +

sandbox_config is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.