middle_click · Hermes Computer Use MCP: Risk & Policy

WHAT IT DOES

What middle_click does on Hermes Computer Use

AI agents invoke middle_click to trigger actions in Hermes Computer Use. 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 middle_click needs a policy

Middle-click performs a browser action that triggers external operations — navigating to URLs and opening new tabs. This is a real browser interaction that can initiate network requests, load pages, and cause cascading side effects depending on what is clicked. It falls squarely in the Execute category as it drives OS-level mouse input on a real browser.

From the tool's definition Move to (x,y) then single middle-click (typically opens link in new tab)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

middle_click Rate-limited

middle_click 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": {
    "middle_click": {
      "limits": [
        {
          "counter": "middle_click_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 Hermes Computer Use, so you can run agents against it safely.

FAQ

Questions about middle_click

What does the middle_click tool do? +

Move to (x,y) then single middle-click (typically opens link in new tab). It is categorised as a Execute tool in the Hermes Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on middle_click? +

Register the Hermes Computer Use MCP server in PolicyLayer and add a rule for middle_click: 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 Hermes Computer Use. Nothing to install.

What risk level is middle_click? +

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

Can I rate-limit middle_click? +

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

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

middle_click is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.