plot_box · ML Research MCP: Risk & Policy

WHAT IT DOES

What plot_box does on ML Research MCP

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

WHY IT NEEDS A POLICY

Why plot_box needs a policy

Based on the server context and sibling tools, plot_box almost certainly generates a box plot (box-and-whisker chart) and writes/saves an output file. The description is empty, lowering confidence, but the pattern is consistent with the other plot_* tools which create visualization artifacts. This is a Write operation (creating a file or figure) with low severity since it only produces a visualization.

From the tool's definition Tool name 'plot_box' on a server explicitly described as generating scientific visualizations and figures; sibling tools are all plot-type tools (plot_bar, plot_scatter, plot_heatmap, etc.)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plot_box Rate-limited

plot_box 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": {
    "plot_box": {
      "limits": [
        {
          "counter": "plot_box_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 ML Research MCP, so you can run agents against it safely.

FAQ

Questions about plot_box

What does the plot_box tool do? +

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

How do I enforce a policy on plot_box? +

Register the ML Research MCP server in PolicyLayer and add a rule for plot_box: 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 ML Research MCP. Nothing to install.

What risk level is plot_box? +

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

Can I rate-limit plot_box? +

Yes. Add a rate_limit block to the plot_box 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 plot_box completely? +

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

plot_box is provided by the ML Research MCP server (nishide-dev/ml-research-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.