stop_all_paragraphs · Zeppelin MCP: Risk & Policy

WHAT IT DOES

What stop_all_paragraphs does on Zeppelin

AI agents invoke stop_all_paragraphs 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 stop_all_paragraphs needs a policy

This tool executes an action that interrupts running processes within Apache Zeppelin. While not destructive (data is not deleted) and not a read operation, it triggers termination of external operations whose outcome depends on runtime state.

From the tool's definition Tool description states 'Cancel all running paragraphs in a notebook' — this actively terminates external operations (paragraph execution) whose effects depend on which paragraphs are running.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_all_paragraphs Rate-limited

stop_all_paragraphs 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": {
    "stop_all_paragraphs": {
      "limits": [
        {
          "counter": "stop_all_paragraphs_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 stop_all_paragraphs

What does the stop_all_paragraphs tool do? +

Cancel all running paragraphs in a notebook. 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 stop_all_paragraphs? +

Register the Zeppelin MCP server in PolicyLayer and add a rule for stop_all_paragraphs: 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 stop_all_paragraphs? +

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

Can I rate-limit stop_all_paragraphs? +

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

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

stop_all_paragraphs 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.