stop_paragraph · Zeppelin MCP: Risk & Policy

WHAT IT DOES

What stop_paragraph does on Zeppelin

AI agents invoke stop_paragraph 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_paragraph needs a policy

stop_paragraph executes a control operation on live Zeppelin paragraph execution. The action depends on argument context (which paragraph, current state) and interrupts an ongoing computational operation, fitting the Execute category.

From the tool's definition Tool performs 'cancel a running paragraph' — an active operation that interrupts execution state in Apache Zeppelin.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_paragraph Rate-limited

stop_paragraph 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_paragraph": {
      "limits": [
        {
          "counter": "stop_paragraph_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_paragraph

What does the stop_paragraph tool do? +

Cancel a running paragraph. 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_paragraph? +

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

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

Can I rate-limit stop_paragraph? +

Yes. Add a rate_limit block to the stop_paragraph 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_paragraph completely? +

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

stop_paragraph 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.