viewer_highlight_clash · PyNet Bridge MCP: Risk & Policy

WHAT IT DOES

What viewer_highlight_clash does on PyNet Bridge

AI agents invoke viewer_highlight_clash to trigger actions in PyNet Bridge. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why viewer_highlight_clash needs a policy

This tool triggers an external UI operation in an open viewer, changing the visual state of displayed elements. It performs an action in an external application (PyNet Platform viewer) rather than simply reading data or persistently modifying stored data. It is an Execute-category action as it drives a UI/viewer interaction whose effects depend on the provided pnt_id arguments.

From the tool's definition Highlights a clash pair in the open viewer by pnt_id (element A red, element B green)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

viewer_highlight_clash Rate-limited

viewer_highlight_clash stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "viewer_highlight_clash": {
      "limits": [
        {
          "counter": "viewer_highlight_clash_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches PyNet Bridge, so you can run agents against it safely.

FAQ

Questions about viewer_highlight_clash

What does the viewer_highlight_clash tool do? +

Highlights a clash pair in the open viewer by pnt_id (element A red, element B green). It is categorised as a Execute tool in the PyNet Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on viewer_highlight_clash? +

Register the PyNet Bridge MCP server in PolicyLayer and add a rule for viewer_highlight_clash: 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 PyNet Bridge. Nothing to install.

What risk level is viewer_highlight_clash? +

viewer_highlight_clash is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit viewer_highlight_clash? +

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

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

viewer_highlight_clash is provided by the PyNet Bridge MCP server (rafael-nunezdearenas/pynetbridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.