Low Risk

plot_edf

plot_edf

How to control plot_edf ↓

AI agents call plot_edf to retrieve information from Optuna MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

EDF plots are read-only visualizations that retrieve and display optimization results without modifying study state, creating new data structures, executing external code, or causing irreversible changes. The tool generates a plot artifact from existing optimization data, consistent with Read category functions that query and analyze results.

From the tool's definition Tool name 'plot_edf' indicates generation of an EDF (empirical distribution function) plot, a standard statistical visualization. Empty description limits certainty, but context shows this is an analysis/reporting tool among optimization functions.

Documented attack patterns abuse exactly the kind of access plot_edf gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Optuna MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for plot_edf:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "plot_edf": {}
  }
}

plot_edf is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Optuna MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the plot_edf tool do? +

plot_edf. It is categorised as a Read tool in the Optuna MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on plot_edf? +

Register the Optuna MCP Server MCP server in PolicyLayer and add a rule for plot_edf: 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 Optuna MCP Server. Nothing to install.

What risk level is plot_edf? +

plot_edf is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit plot_edf? +

Yes. Add a rate_limit block to the plot_edf 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_edf completely? +

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

plot_edf is provided by the Optuna MCP Server MCP server (optuna/optuna-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Optuna MCP Server tool call.

Deterministic rules across all 26 Optuna MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

26 Optuna MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.