run_job · Cloudera Machine Learning (CML) MCP Server MCP

WHAT IT DOES

What run_job does on Cloudera Machine Learning (CML) MCP Server

AI agents invoke run_job to trigger actions in Cloudera Machine Learning (CML) MCP Server. 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_job needs a policy

This tool triggers execution of a predefined job whose behavior and side effects depend on what the job contains. While not as severe as Execute tools that accept arbitrary code directly (like execute_script), running a job can cause significant unintended consequences (resource consumption, data processing, model retraining, external API calls) if an AI agent selects the wrong job or runs it in the wrong context.

From the tool's definition Tool name is 'run_job' and description states it will 'Run a job in a CML project.' Jobs in ML contexts can execute arbitrary code, training pipelines, data processing workflows, or scripts whose effects depend on the job definition and arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_job Rate-limited

run_job 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_job": {
      "limits": [
        {
          "counter": "run_job_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 Cloudera Machine Learning (CML) MCP Server, so you can run agents against it safely.

FAQ

Questions about run_job

What does the run_job tool do? +

Run a job in a CML project. It is categorised as a Execute tool in the Cloudera Machine Learning (CML) MCP Server 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_job? +

Register the Cloudera Machine Learning (CML) MCP Server MCP server in PolicyLayer and add a rule for run_job: 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 Cloudera Machine Learning (CML) MCP Server. Nothing to install.

What risk level is run_job? +

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

Can I rate-limit run_job? +

Yes. Add a rate_limit block to the run_job 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_job completely? +

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

run_job is provided by the Cloudera Machine Learning (CML) MCP Server MCP server (yw449/cloudera-cml-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.