plot_signals · Mdf MCP: Risk & Policy

WHAT IT DOES

What plot_signals does on Mdfmcp

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

WHY IT NEEDS A POLICY

Why plot_signals needs a policy

The tool creates a plot, which is a write operation generating a new output artifact. It does not delete data or execute arbitrary code, but it produces a file or visual output. Severity is medium since misuse could generate misleading visualizations or consume resources, but there is no irreversible destructive action.

From the tool's definition 'Create a plot of one or more signals' — creates a new artifact (a plot/image file)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plot_signals Rate-limited

plot_signals 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_signals": {
      "limits": [
        {
          "counter": "plot_signals_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 Mdfmcp, so you can run agents against it safely.

FAQ

Questions about plot_signals

What does the plot_signals tool do? +

Create a plot of one or more signals. It is categorised as a Write tool in the Mdfmcp 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_signals? +

Register the Mdf MCP server in PolicyLayer and add a rule for plot_signals: 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 Mdfmcp. Nothing to install.

What risk level is plot_signals? +

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

Can I rate-limit plot_signals? +

Yes. Add a rate_limit block to the plot_signals 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_signals completely? +

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

plot_signals is provided by the Mdf MCP server (shanko-26/mdfmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.