handoff · Headroom MCP: Risk & Policy

WHAT IT DOES

What handoff does on Headroom

AI agents use handoff to create or update resources in Headroom — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Headroom environment.

WHY IT NEEDS A POLICY

Why handoff needs a policy

This tool writes to a document that serves as state for task resumption. While the update is reversible and not destructive, and no external operations or financial transactions occur, it clearly modifies data.

From the tool's definition Tool description states "Update YOUR canonical handoff document" — the verb "Update" indicates modification of data (the handoff document). The tool creates or modifies a persistent markdown document that persists across Claude instances.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

handoff Rate-limited

handoff stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "handoff": {
      "limits": [
        {
          "counter": "handoff_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Headroom, so you can run agents against it safely.

FAQ

Questions about handoff

What does the handoff tool do? +

Update YOUR canonical handoff document — the living markdown working-doc a fresh instance of you would read to resume this work fully. Richer and more durable than. It is categorised as a Write tool in the Headroom MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on handoff? +

Register the Headroom MCP server in PolicyLayer and add a rule for 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 Headroom. Nothing to install.

What risk level is handoff? +

handoff is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit handoff? +

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

Set action: deny in the PolicyLayer policy for 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 handoff? +

handoff is provided by the Headroom MCP server (tyejcoleman/headroom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.