prompt

THE RISK

Low Risk

Why prompt needs a policy

The description is empty and uninformative. While the server context involves GUI automation, the tool name 'prompt' alone does not clearly indicate a specific category. It could relate to the 'prompt' dialog (similar to alert/confirm siblings), but without evidence I cannot confidently classify it beyond Other.

From the tool's definition Tool name is 'prompt' with an empty description. No information available about what this tool does.

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

POLICY

How to control prompt

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "prompt": {
      "limits": [
        {
          "counter": "prompt_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

prompt gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register PyMCPAutoGUI — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More PyMCPAutoGUI tools

Destructive close_window Closes the first window matching the title. Execute activate_window Activates (brings to the front) the first window matching the title. Execute alert alert Execute click click Execute confirm confirm Execute drag_rel drag_rel Execute drag_to drag_to Execute hotkey hotkey

All 34 PyMCPAutoGUI tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about prompt

What does the prompt tool do? +

prompt. It is categorised as a Other tool in the PyMCPAutoGUI MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on prompt? +

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

What risk level is prompt? +

prompt is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit prompt? +

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

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

prompt is provided by the PyMCPAutoGUI MCP server (kitfactory/pymcpautogui). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PyMCPAutoGUI tool call.

Start from PyMCPAutoGUI, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →