run_cell · Jlab MCP: Risk & Policy

WHAT IT DOES

What run_cell does on Jlab

AI agents invoke run_cell to trigger actions in Jlab. 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_cell needs a policy

run_cell executes arbitrary Python code on remote HPC resources. This is Execute-class because code execution effects depend entirely on arguments (what Python code is run). The high-performance GPU compute context and SLURM job integration amplify potential impact—malicious or erroneous Python could consume significant cluster resources, access sensitive data, or trigger unwanted computations.

From the tool's definition Tool name 'run_cell' in context of JupyterLab execution server; sibling tools include 'execute_code' and 'execute_scratch'; server description explicitly states it 'enables LLMs to execute Python code on GPU-accelerated compute nodes'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_cell Rate-limited

run_cell 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_cell": {
      "limits": [
        {
          "counter": "run_cell_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 Jlab, so you can run agents against it safely.

FAQ

Questions about run_cell

What does the run_cell tool do? +

run_cell. It is categorised as a Execute tool in the Jlab 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_cell? +

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

What risk level is run_cell? +

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

Can I rate-limit run_cell? +

Yes. Add a rate_limit block to the run_cell 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_cell completely? +

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

run_cell is provided by the Jlab MCP server (kdkyum/jlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.