gui_act · Local M MCP: Risk & Policy

WHAT IT DOES

What gui_act does on Local Mmcp

AI agents invoke gui_act to trigger actions in Local Mmcp. 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 gui_act needs a policy

GUI automation tools that 'act' on the interface execute operations such as clicking, typing, and navigating applications. Given the server's explicit mention of 'GUI automation', this tool almost certainly triggers external GUI operations. Empty description lowers confidence but the sibling tool 'gui_observe' (read) contrasts with 'gui_act' (execute/write), suggesting this tool performs actions.

From the tool's definition Tool name 'gui_act' on a server described as including 'GUI automation'. The description is empty, lowering confidence, but the name strongly implies GUI action execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gui_act Rate-limited

gui_act 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": {
    "gui_act": {
      "limits": [
        {
          "counter": "gui_act_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 Local Mmcp, so you can run agents against it safely.

FAQ

Questions about gui_act

What does the gui_act tool do? +

gui_act. It is categorised as a Execute tool in the Local Mmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gui_act? +

Register the Local M MCP server in PolicyLayer and add a rule for gui_act: 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 Local Mmcp. Nothing to install.

What risk level is gui_act? +

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

Can I rate-limit gui_act? +

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

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

gui_act is provided by the Local M MCP server (rorojiao/local-mmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.