computer_wait · Computer Use MCP Server MCP: Risk & Policy

WHAT IT DOES

What computer_wait does on Computer Use MCP Server

AI agents invoke computer_wait to trigger actions in Computer Use MCP Server. 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 computer_wait needs a policy

This tool executes a timed pause operation, which is a direct instruction to the system to perform an action (delay execution). While it has no side effects on data, it is an Execute category tool because it triggers an external operation (system sleep/pause) whose effect depends on the argument (duration).

From the tool's definition Tool performs a pause/wait action that is part of the Computer Use MCP Server's suite of automation tools. Described as 'Wait/pause for a specified duration in seconds' to let UI settle before subsequent actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

computer_wait Rate-limited

computer_wait 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": {
    "computer_wait": {
      "limits": [
        {
          "counter": "computer_wait_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 Computer Use MCP Server, so you can run agents against it safely.

FAQ

Questions about computer_wait

What does the computer_wait tool do? +

Wait/pause for a specified duration in seconds. Useful to let UI settle. It is categorised as a Execute tool in the Computer Use MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on computer_wait? +

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

What risk level is computer_wait? +

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

Can I rate-limit computer_wait? +

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

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

computer_wait is provided by the Computer Use MCP Server MCP server (sebastianbaltes/claude_code_computer_use_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.