Human Handoff relay

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

Hands CAPTCHAs, 2FA codes and approvals from your agent to your human with one tap.

Deletes · 1Changes · 3

Compare Registry entry

5 tools: 1 can delete or cancel things, 3 change things and 1 only read.

Scanned Oct 21, 2026

Deletes or cancels1Claude Code: deny: see these tools
Can't be undone0Claude Code: ask
Changes things3Claude Code: ask: see these tools
Only reads1Claude Code: allow: see these tools

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

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

Tools

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

5 tools

Deletes or cancels 1Removes, cancels or revokes something.Claude Code: deny

cancel_requestCancel a pending request (for example your agent got past the step another way).No findings
Why it is in this group
- The name "cancel_request" says "cancel": a word for removing or ending something.
Description, as the server wrote it
Cancel a pending request (for example your agent got past the step another way). The link stops working and any unread code is wiped.

Changes things 3Creates or changes something that can be changed back.Claude Code: ask

check_requestPoll a request: pending, done, approved, denied, code_ready, expired or cancelled.No findings
Why it is in this group
- The name "check_request" says "request": a word for a change.
Description, as the server wrote it
Poll a request: pending, done, approved, denied, code_ready, expired or cancelled. For 2fa_code, the code is returned exactly once (single read) and only within 10 minutes of the person sending it; then it is wiped.
request_humanHand one blocked step to your human: a CAPTCHA, a 2FA/OTP code, an approval, or a sign-in your agent should not do alone.Can send data outNo findings
Why it is in this group
- The name "request_human" says "request": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
Hand one blocked step to your human: a CAPTCHA, a 2FA/OTP code, an approval, or a sign-in your agent should not do alone. Pro acts: sends your person a one-tap link (to notify_webhook, Slack/Discord-compatible, and/or notify_email), returns request_id, and later an HMAC-signed POST to callback_url when they answer. Free watch-only logs a would_request for the weekly stuck report and sends nothing. We never solve CAPTCHAs and never ask for passwords.
weekly_reportPlain-English summary of the last 7 days: where your agent got stuck (by kind and by site), requests sent or that would have been, how many your person answered and how fast.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
Plain-English summary of the last 7 days: where your agent got stuck (by kind and by site), requests sent or that would have been, how many your person answered and how fast. Read-only; sends nothing. Needs a free API key.

Only reads 1Looks things up and changes nothing.Claude Code: allow

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.; request_human

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

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 15:21 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 4
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

HighThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 destructive, 3 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://relay.cloudforbots.com/mcp: tools/list returned 5 tools to an anonymous client, including cancel_request (destructive), request_human (write), check_request (write), weekly_report (write)
What this check looks for

Install

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

claude mcp add --transport http relay https://relay.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__relay__usage_and_upgrade"
    ],
    "ask": [
      "mcp__relay__request_human",
      "mcp__relay__check_request",
      "mcp__relay__weekly_report"
    ],
    "deny": [
      "mcp__relay__cancel_request"
    ]
  }
}

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 relay. Review it before you use it.

Capability tags behind 1 rule

mcp__relay__request_human outbound

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/com.botrecipe/relay/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

4 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 17:52 UTC.

For agents: Markdown · JSON · report this listing