suggest_action · Uitars MCP: Risk & Policy

WHAT IT DOES

What suggest_action does on Uitars

AI agents invoke suggest_action to trigger actions in Uitars. 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 suggest_action needs a policy

This tool analyzes the screen and suggests (and likely triggers) click or type actions to achieve a goal. Since it drives GUI automation — performing clicks and keystrokes on the live desktop — it falls under Execute. Misuse could result in unintended GUI interactions, data submission, or launching applications.

From the tool's definition suggest_action: 'Analyze screen and suggest the next click/type action to achieve a goal' — triggers click/type actions on the GUI

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

suggest_action Rate-limited

suggest_action 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": {
    "suggest_action": {
      "limits": [
        {
          "counter": "suggest_action_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 Uitars, so you can run agents against it safely.

FAQ

Questions about suggest_action

What does the suggest_action tool do? +

Analyze screen and suggest the next click/type action to achieve a goal. It is categorised as a Execute tool in the Uitars MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on suggest_action? +

Register the Uitars MCP server in PolicyLayer and add a rule for suggest_action: 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 Uitars. Nothing to install.

What risk level is suggest_action? +

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

Can I rate-limit suggest_action? +

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

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

suggest_action is provided by the Uitars MCP server (lxsoftroxs/uitars-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.