Medium Risk

plot_math_function

Generates a 2D plot. Tries Desmos API if available, otherwise falls back to local rendering.

How to control plot_math_function ↓

What plot_math_function does on Desmos MCP Server

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

Medium Risk

Why plot_math_function needs a policy

The tool creates a new graphical output (a 2D plot) either via the Desmos API or local matplotlib rendering. This is a Write operation since it produces a new artifact. It does not execute arbitrary code, delete data, or involve finances. Severity is medium because it writes files or makes API calls, but the blast radius is limited to plot generation.

From the tool's definition 'Generates a 2D plot' and 'falls back to local rendering' — creates a plot artifact (file or rendered output) as a side effect

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

How to control plot_math_function

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "plot_math_function": {
      "limits": [
        {
          "counter": "plot_math_function_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

plot_math_function 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.

  1. Create a free account and register Desmos 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.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about plot_math_function

What does the plot_math_function tool do? +

Generates a 2D plot. Tries Desmos API if available, otherwise falls back to local rendering. It is categorised as a Write tool in the Desmos MCP Server 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_math_function? +

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

What risk level is plot_math_function? +

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

Can I rate-limit plot_math_function? +

Yes. Add a rate_limit block to the plot_math_function 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_math_function completely? +

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

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

Enforce policy on every Desmos MCP Server tool call.

Start from Desmos MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

5 Desmos MCP Server tools catalogued and risk-classified — across an index of 43,000+ 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.