save_sandbox_spec · Swarm MCP: Risk & Policy

WHAT IT DOES

What save_sandbox_spec does on Swarm

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

WHY IT NEEDS A POLICY

Why save_sandbox_spec needs a policy

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

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_sandbox_spec Rate-limited

save_sandbox_spec 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": {
    "save_sandbox_spec": {
      "limits": [
        {
          "counter": "save_sandbox_spec_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 Swarm, so you can run agents against it safely.

FAQ

Questions about save_sandbox_spec

What does the save_sandbox_spec tool do? +

save_sandbox_spec. It is categorised as a Write tool in the Swarm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_sandbox_spec? +

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

What risk level is save_sandbox_spec? +

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

Can I rate-limit save_sandbox_spec? +

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

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

save_sandbox_spec is provided by the Swarm MCP server (stiege/swarm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.