fetch_handoff · Claude Handoff MCP: Risk & Policy

WHAT IT DOES

What fetch_handoff does on Claude Handoff

AI agents invoke fetch_handoff to trigger actions in Claude Handoff. 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 fetch_handoff needs a policy

This tool fetches remote content from a URL and extracts an archive to a temp directory on the local filesystem. The network fetch and archive extraction constitute external operations with side effects (writing files to disk, executing decompression).

From the tool's definition 'Fetch a Claude Design handoff bundle from its URL and extract it to a temp directory' — downloads content from an external URL and extracts it (e.g., gzipped tar) to the filesystem

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fetch_handoff Rate-limited

fetch_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": {
    "fetch_handoff": {
      "limits": [
        {
          "counter": "fetch_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 Claude Handoff, so you can run agents against it safely.

FAQ

Questions about fetch_handoff

What does the fetch_handoff tool do? +

Fetch a Claude Design handoff bundle from its URL and extract it to a temp directory. Supports HTML bundles (gzipped tar), PPTX, and PDF. Handoff URLs have a TTL and may be single-use — fetch promptly. It is categorised as a Execute tool in the Claude Handoff MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on fetch_handoff? +

Register the Claude Handoff MCP server in PolicyLayer and add a rule for fetch_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 Claude Handoff. Nothing to install.

What risk level is fetch_handoff? +

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

Can I rate-limit fetch_handoff? +

Yes. Add a rate_limit block to the fetch_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 fetch_handoff completely? +

Set action: deny in the PolicyLayer policy for fetch_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 fetch_handoff? +

fetch_handoff is provided by the Claude Handoff MCP server (kiwuuu/claude-handoff-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.