run_all_paragraphs · Zeppelin MCP: Risk & Policy

WHAT IT DOES

What run_all_paragraphs does on Zeppelin

AI agents invoke run_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 run_all_paragraphs needs a policy

This tool executes arbitrary code with effects determined by the notebook contents, which an AI agent may not fully understand. The blast radius is high because notebooks can contain destructive commands (delete database records, modify data, trigger external systems) or expensive operations (large queries, computations). Unlike a simple Read operation, this commits to side effects.

From the tool's definition Tool runs all paragraphs in a notebook sequentially. Each paragraph can execute arbitrary code (SQL, Python, Scala, shell commands, etc.) through Apache Zeppelin interpreters. The description 'Execute all paragraphs' directly indicates execution of code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_all_paragraphs Rate-limited

run_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": {
    "run_all_paragraphs": {
      "limits": [
        {
          "counter": "run_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 run_all_paragraphs

What does the run_all_paragraphs tool do? +

Execute all paragraphs in a notebook sequentially. 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 run_all_paragraphs? +

Register the Zeppelin MCP server in PolicyLayer and add a rule for run_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 run_all_paragraphs? +

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

Can I rate-limit run_all_paragraphs? +

Yes. Add a rate_limit block to the run_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 run_all_paragraphs completely? +

Set action: deny in the PolicyLayer policy for run_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 run_all_paragraphs? +

run_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.