restart_interpreter · Zeppelin MCP: Risk & Policy

WHAT IT DOES

What restart_interpreter does on Zeppelin

AI agents invoke restart_interpreter to trigger actions in Zeppelin. 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 restart_interpreter needs a policy

This tool executes a command to restart an interpreter, which is an external operation whose effects depend on which interpreter is specified. It affects running notebooks and paragraphs but is not destructive (data is not deleted) and not financial. It fits Execute because it performs a system action that changes operational state.

From the tool's definition Tool name 'restart_interpreter' and description indicate it restarts a Zeppelin interpreter—a runtime component. Restarting an interpreter is an operational action that triggers external state changes in the Zeppelin system, clearing memory and session state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

restart_interpreter Rate-limited

restart_interpreter 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": {
    "restart_interpreter": {
      "limits": [
        {
          "counter": "restart_interpreter_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 Zeppelin, so you can run agents against it safely.

FAQ

Questions about restart_interpreter

What does the restart_interpreter tool do? +

Restart a Zeppelin interpreter by setting name (e.g. It is categorised as a Execute tool in the Zeppelin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on restart_interpreter? +

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

What risk level is restart_interpreter? +

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

Can I rate-limit restart_interpreter? +

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

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

restart_interpreter is provided by the Zeppelin MCP server (mihneamanolache/zeppelin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.