tool_export_graph · origin- MCP: Risk & Policy

WHAT IT DOES

What tool_export_graph does on origin-MCP

AI agents use tool_export_graph 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_export_graph needs a policy

This tool creates or writes data (an image file) to disk, which is a reversible Write operation. It does not execute arbitrary code, delete data, or move money. The blast radius is minimal—an exported file can be deleted or regenerated. Confidence is high because the description clearly indicates file creation/output behavior without any destructive or execute semantics.

From the tool's definition tool_export_graph exports a graph to an image file in multiple formats (PNG, SVG, EMF, PDF, JPG, TIF, BMP, EPS) with configurable parameters (width, height, DPI, transparency). The action creates a new file on the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tool_export_graph Rate-limited

tool_export_graph 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_export_graph": {
      "limits": [
        {
          "counter": "tool_export_graph_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_export_graph

What does the tool_export_graph tool do? +

Export a graph to an image file (PNG, SVG, EMF, PDF, JPG, TIF, BMP, EPS). Control width, height, DPI, and transparency. 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_export_graph? +

Register the origin- MCP server in PolicyLayer and add a rule for tool_export_graph: 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_export_graph? +

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

Can I rate-limit tool_export_graph? +

Yes. Add a rate_limit block to the tool_export_graph 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_export_graph completely? +

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

tool_export_graph 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.