edit_markdown · Jlab MCP: Risk & Policy

WHAT IT DOES

What edit_markdown does on Jlab

AI agents use edit_markdown 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_markdown needs a policy

This tool modifies notebook markdown cells reversibly—changes can be undone by editing again or restoring prior notebook states. It does not delete data (ruling out Destructive), does not execute code (ruling out Execute), and does not create financial obligations. While the server runs on GPU-accelerated HPC clusters, editing markdown itself has no direct computational impact.

From the tool's definition Tool name 'edit_markdown' and description 'Edit an existing markdown cell's content' indicate modification of existing data within a JupyterLab notebook session.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

edit_markdown Rate-limited

edit_markdown 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_markdown": {
      "limits": [
        {
          "counter": "edit_markdown_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_markdown

What does the edit_markdown tool do? +

Edit an existing markdown cell's content. 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_markdown? +

Register the Jlab MCP server in PolicyLayer and add a rule for edit_markdown: 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_markdown? +

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

Can I rate-limit edit_markdown? +

Yes. Add a rate_limit block to the edit_markdown 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_markdown completely? +

Set action: deny in the PolicyLayer policy for edit_markdown. 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_markdown? +

edit_markdown 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.