ui_redo · UI Bridge MCP: Risk & Policy

WHAT IT DOES

What ui_redo does on UI Bridge MCP

AI agents invoke ui_redo to trigger actions in UI Bridge MCP. 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 ui_redo needs a policy

The tool executes a redo action, which is a user-interface operation that modifies application state. While redo operations are typically reversible (via undo), they represent executable commands that change the UI/application state based on what the user previously undid.

From the tool's definition Tool name 'ui_redo' and description 'Execute redo in the runner' indicate this performs an action (redo operation) that triggers UI state changes on the runner's own interface.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ui_redo Rate-limited

ui_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": {
    "ui_redo": {
      "limits": [
        {
          "counter": "ui_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 UI Bridge MCP, so you can run agents against it safely.

FAQ

Questions about ui_redo

What does the ui_redo tool do? +

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

How do I enforce a policy on ui_redo? +

Register the UI Bridge MCP server in PolicyLayer and add a rule for ui_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 UI Bridge MCP. Nothing to install.

What risk level is ui_redo? +

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

Can I rate-limit ui_redo? +

Yes. Add a rate_limit block to the ui_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 ui_redo completely? +

Set action: deny in the PolicyLayer policy for ui_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 ui_redo? +

ui_redo is provided by the UI Bridge MCP server (qontinui/ui-bridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.