sandy_check · Sandy MCP: Risk & Policy

WHAT IT DOES

What sandy_check does on Sandy

AI agents invoke sandy_check to trigger actions in Sandy. 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 IT NEEDS A POLICY

Why sandy_check needs a policy

The tool runs an operation (health check) in the sandboxed environment, which constitutes execution rather than a pure read. However, it is scoped to a baseline/connectivity check with an ephemeral session, limiting blast radius. Severity is low because health checks are read-like diagnostics with no data modification, but the execution context (AWS SDK sandbox) warrants the Execute category over Read.

From the tool's definition 'Run a health check' and 'Uses an ephemeral session' — actively executes a check operation in the sandboxed environment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandy_check Rate-limited

sandy_check 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandy_check": {
      "limits": [
        {
          "counter": "sandy_check_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about sandy_check

What does the sandy_check tool do? +

Run a health check (baseline or connect). Uses an ephemeral session. It is categorised as a Execute tool in the Sandy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sandy_check? +

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

What risk level is sandy_check? +

sandy_check is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sandy_check? +

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

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

sandy_check is provided by the Sandy MCP server (jamestelfer/sandy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.