High Risk →

press_mouse

Press down a mouse button at the specified coordinates

How to control press_mouse ↓

What press_mouse does on Mcp Autogui Multinode

AI agents invoke press_mouse to trigger actions in Mcp Autogui Multinode. 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.

High Risk

Why press_mouse needs a policy

This tool simulates a physical mouse button press at specified coordinates on a local or remote system. It triggers external UI interactions whose effects depend entirely on what is on screen at those coordinates — could invoke buttons, links, context menus, or drag operations.

From the tool's definition Press down a mouse button at the specified coordinates

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

How to control press_mouse

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "press_mouse": {
      "limits": [
        {
          "counter": "press_mouse_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

press_mouse 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.

  1. Create a free account and register Mcp Autogui Multinode — 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.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about press_mouse

What does the press_mouse tool do? +

Press down a mouse button at the specified coordinates. It is categorised as a Execute tool in the Mcp Autogui Multinode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on press_mouse? +

Register the Mcp Autogui Multinode MCP server in PolicyLayer and add a rule for press_mouse: 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 Mcp Autogui Multinode. Nothing to install.

What risk level is press_mouse? +

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

Can I rate-limit press_mouse? +

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

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

press_mouse is provided by the Mcp Autogui Multinode MCP server (stonehill-2345/mcp-autogui-multinode). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Autogui Multinode tool call.

Start from Mcp Autogui Multinode, 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.

11 Mcp Autogui Multinode 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.