Skip to content

Handoff Watch

by botrecipe.com · remote · no sign-in to list tools · v1.0.0 · published by com.botrecipe

Spots stalled agent-to-agent tasks and nudges or reassigns them. Works beside Offhand.

Changes · 2
CompareRegistry entry

4 tools: 2 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http handoff https://handoff.cloudforbots.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 2Claude Code: ask
  • scan_handoffsPass the tasks your agents handed each other (e.g.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.webhooks): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Pass the tasks your agents handed each other (e.g. the result of Offhand list_todos) and get back which are stalled or failing and what to do. A task is stalled when it is claimed (in_progress) or handed over but untouched for stall_minutes, and failing when it is blocked or has failed fail_limit times. Ladder: nudge the assignee, nudge again, then reassign to a backup agent (or ask the person). Pro acts: records each nudge with a cooldown so nobody is pinged twice, and POSTs the nudge to the agent's webhook if you give one. Free watch-only takes no action and returns would_nudge / would_reassign. It never changes a task in Offhand itself and never takes a task another agent holds; reassigning returns an Offhand add_task call for your agent to make.
  • weekly_reportDraft a plain-English report of the last 7 days: stalled tasks found, nudges and reassigns made (Pro) or that would have been made (free).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Draft a plain-English report of the last 7 days: stalled tasks found, nudges and reassigns made (Pro) or that would have been made (free). Read-only; sends nothing.
Only reads 2Claude Code: allow
  • nudge_logList the latest nudges and reassigns (Pro) or would-nudges (free) for one board or all boards on your key.No findings

    Why it is in this group

    • The name "nudge_log" says "log": a word for reading.
    Description, as the server wrote it
    List the latest nudges and reassigns (Pro) or would-nudges (free) for one board or all boards on your key.
  • usage_and_upgradeShow today's usage for your key or IP and the $9/month upgrade link.No findings

    Why it is in this group

    • The description's first verb is "show": a word for reading.
    Description, as the server wrote it
    Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http handoff https://handoff.cloudforbots.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__handoff__nudge_log",
      "mcp__handoff__usage_and_upgrade"
    ],
    "ask": [
      "mcp__handoff__scan_handoffs",
      "mcp__handoff__weekly_report"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as handoff. Review it before you use it.

Capability tags behind 1 rule
  • mcp__handoff__scan_handoffs outbound