tool_create_plot · origin- MCP: Risk & Policy

WHAT IT DOES

What tool_create_plot does on origin-MCP

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

WHY IT NEEDS A POLICY

Why tool_create_plot needs a policy

The tool creates a plot object, which is a reversible operation—plots can be deleted or modified. This is Write rather than Execute because it does not run arbitrary code or trigger external operations; it structures data for visualization. The empty description reduces confidence somewhat, but the name and context strongly suggest plot creation rather than querying (Read) or deleting (Destructive).

From the tool's definition Tool name 'tool_create_plot' combined with sibling tools like 'tool_add_plot_to_graph', 'tool_add_text_annotation', 'tool_create_grouped_plot', and 'tool_create_multi_curve_plot' indicates this tool creates or modifies data structures within Origin 2025b.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tool_create_plot Rate-limited

tool_create_plot 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": {
    "tool_create_plot": {
      "limits": [
        {
          "counter": "tool_create_plot_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 origin-MCP, so you can run agents against it safely.

FAQ

Questions about tool_create_plot

What does the tool_create_plot tool do? +

tool_create_plot. It is categorised as a Write tool in the origin-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 tool_create_plot? +

Register the origin- MCP server in PolicyLayer and add a rule for tool_create_plot: 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 origin-MCP. Nothing to install.

What risk level is tool_create_plot? +

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

Can I rate-limit tool_create_plot? +

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

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

tool_create_plot is provided by the origin- MCP server (zhang-923-ze/origin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.