redo · Hermes Computer Use MCP: Risk & Policy

WHAT IT DOES

What redo does on Hermes Computer Use

AI agents invoke redo to trigger actions in Hermes Computer Use. 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 redo needs a policy

This tool triggers a keyboard action (Ctrl+Shift+Z) in a real browser via OS-level input, re-applying a previously undone edit. It is an external browser operation whose effect depends on context. While often benign, in a pixel-level browser automation environment it could re-apply significant edits, making it an Execute-category action with medium severity.

From the tool's definition Redo the last undone edit (ctrl+shift+z)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

redo Rate-limited

redo 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": {
    "redo": {
      "limits": [
        {
          "counter": "redo_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 Hermes Computer Use, so you can run agents against it safely.

FAQ

Questions about redo

What does the redo tool do? +

Redo the last undone edit (ctrl+shift+z). It is categorised as a Execute tool in the Hermes Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on redo? +

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

What risk level is redo? +

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

Can I rate-limit redo? +

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

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

redo is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.