edit_cell · Jlab MCP: Risk & Policy

WHAT IT DOES

What edit_cell does on Jlab

AI agents use edit_cell to create or update resources in Jlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jlab environment.

WHY IT NEEDS A POLICY

Why edit_cell needs a policy

The tool modifies cell contents in a JupyterLab session running on GPU-accelerated HPC nodes. This is reversible (Write rather than Destructive), but carries high severity because: (1) modified cells can be executed to run arbitrary code on HPC infrastructure, (2) it could alter scientific computations or data processing pipelines, and (3) the blast radius extends to shared cluster resources.

From the tool's definition Tool name 'edit_cell' combined with sibling tools 'execute_code', 'run_cell', and 'delete_cell' in a Jupyter/HPC execution environment. While the description is empty, the context strongly indicates this modifies notebook cell content.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

edit_cell Rate-limited

edit_cell stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "edit_cell": {
      "limits": [
        {
          "counter": "edit_cell_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 edit_cell

What does the edit_cell tool do? +

edit_cell. It is categorised as a Write tool in the Jlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on edit_cell? +

Register the Jlab MCP server in PolicyLayer and add a rule for edit_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 edit_cell? +

edit_cell is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit edit_cell? +

Yes. Add a rate_limit block to the edit_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 edit_cell completely? +

Set action: deny in the PolicyLayer policy for edit_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 edit_cell? +

edit_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.