scout_handoff · Scout MCP: Risk & Policy

WHAT IT DOES

What scout_handoff does on Scout

AI agents invoke scout_handoff to trigger actions in Scout. 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 scout_handoff needs a policy

The tool actively modifies the live browser session by injecting a UI element (banner) and initiates a workflow requiring human intervention. This is an external operation with real side effects on the browser environment, placing it in the Execute category.

From the tool's definition 'Inject a banner in the live browser asking the user to take a manual action' — triggers an external browser UI operation that prompts user interaction in the live session.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scout_handoff Rate-limited

scout_handoff 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": {
    "scout_handoff": {
      "limits": [
        {
          "counter": "scout_handoff_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 Scout, so you can run agents against it safely.

FAQ

Questions about scout_handoff

What does the scout_handoff tool do? +

Inject a banner in the live browser asking the user to take a manual action. Returns IMMEDIATELY with a handoff_id — does NOT block. Poll scout_handoff_check(handoff_id) every 5-10 seconds until status is. It is categorised as a Execute tool in the Scout MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on scout_handoff? +

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

What risk level is scout_handoff? +

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

Can I rate-limit scout_handoff? +

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

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

scout_handoff is provided by the Scout MCP server (lautrek/scout). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.