Skip to content

LIVEAIHELP — Hire a Live Human Expert MCP server

live.helpai/liveaihelphelpai.livestreamable-httpv1.0.1Scanned

Hire a vetted human expert live via chat or video when your AI agent gets stuck. $1/min.

6 tools: 1 can delete or cancel things, 1 do something that can't be undone, 3 change things and 1 only read.

Tools: 1 delete, 1 irreversible, 3 write, 1 read.
  • Reads private data · 1
  • Reads text others write · 5
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the LIVEAIHELP — Hire a Live Human Expert MCP server can do

The LIVEAIHELP — Hire a Live Human Expert MCP server is published by helpai.live, a domain the MCP Registry verified. It has 6 tools. It can delete or cancel things (1 tool: end_session), do things that cannot be undone, such as sending, paying or publishing (send_message) and create or change data (3 tools: hire_human_expert, check_queue and check_balance). 1 tool only reads.

1 tool reads private data (read_messages); 5 tools bring in text other people can write (hire_human_expert, send_message, read_messages and 2 more); 1 tool can send data out of your system (send_message). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 10, 2026, version 1.0.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Deletes or cancels 1Claude Code: deny
  • end_sessionEnd the session when the task is done.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    End the session when the task is done. This stops billing immediately. Always call this when you are finished.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
Can't be undone 1Claude Code: ask
  • send_messageSend a chat message to the human expert in an active session.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_message" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_message" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a chat message to the human expert in an active session. You are the customer in this conversation.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 3Claude Code: ask
  • check_balanceCheck the minute balance of the connected LIVEAIHELP account.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check the minute balance of the connected LIVEAIHELP account.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_queueCheck your position in the expert holding queue.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Check your position in the expert holding queue. Poll until status is matched, then use the returned session_id with send_message / read_messages.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • hire_human_expertHire a live vetted human expert for help with a task.Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Hire a live vetted human expert for help with a task. The expert joins a real-time session (chat or video) and works the problem with you. Sessions draw on the connected account's LIVEAIHELP minute balance. If no expert is online you are placed in a FIFO holding queue — poll check_queue until matched. Chat mode is recommended for AI agents.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • read_messagesRead new chat messages from the human expert.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "read_messages" says "read": a word for reading.

    What it can reach

    • private-dataThe name "read_messages" says "read" and "message": it reads messages.
    • private-dataThe description's first sentence says "read" and "chat": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "read_messages" says "read" and "message": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Read new chat messages from the human expert. Poll this after sending a message to get the expert's reply. Returns the session status too — when status becomes ended or cancelled, stop polling and wrap up.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

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.

5 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write5
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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__liveaihelp__send_message"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 17, 2026, 15:24 UTC, unchanged since Nov 3, 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
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://www.helpai.live/.well-known/oauth-protected-resource
Authorization servers
https://www.helpai.live
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (1 destructive, 1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.helpai.live/api/mcp: tools/list returned 6 tools to an anonymous client, including end_session (destructive), send_message (irreversible), hire_human_expert (write), check_queue (write), check_balance (write)

    What this check looks for

Posture changes

  1. Nov 3, 2026
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 5
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: no to not observed
    • RFC 9728 protected resource metadata: none to https://www.helpai.live/.well-known/oauth-protected-resource
    • Authorization servers: none to https://www.helpai.live
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 401 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 5 (and 6 more).View diff
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 5
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: no to not observed
    • RFC 9728 protected resource metadata: none to https://www.helpai.live/.well-known/oauth-protected-resource
    • Authorization servers: none to https://www.helpai.live
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http liveaihelp https://www.helpai.live/api/mcp
claude mcp add --transport http liveaihelp https://www.helpai.live/api/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__liveaihelp__read_messages"
    ],
    "ask": [
      "mcp__liveaihelp__hire_human_expert",
      "mcp__liveaihelp__send_message",
      "mcp__liveaihelp__check_queue",
      "mcp__liveaihelp__check_balance"
    ],
    "deny": [
      "mcp__liveaihelp__end_session"
    ]
  }
}

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 liveaihelp. Review it before you use it.

Capability tags behind 5 rules
  • mcp__liveaihelp__hire_human_expert untrusted-input
  • mcp__liveaihelp__send_message untrusted-input, outbound
  • mcp__liveaihelp__read_messages private-data, untrusted-input
  • mcp__liveaihelp__check_queue untrusted-input
  • mcp__liveaihelp__end_session untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/live.helpai/liveaihelp/verify?hash=409d961582fa13439e1bb77cd392e4f1745840d2ef85f8e884907ffe79dc275b" | jq -e '.changed == false'

Pinned hash 409d961582fa, from Nov 10, 2026, 19:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/live.helpai/liveaihelp/changes.xml

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

Badge

Anlyon Radar badge for live.helpai/liveaihelp
[![Anlyon Radar](https://radar.anlyon.com/badge/live.helpai/liveaihelp.svg)](https://radar.anlyon.com/servers/live.helpai/liveaihelp)

Source: MCP Registry · repository. Synced Nov 10, 2026, 20:20 UTC.

LIVEAIHELP — Hire a Live Human Expert MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the LIVEAIHELP — Hire a Live Human Expert MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the LIVEAIHELP — Hire a Live Human Expert MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: end_session.

Can the LIVEAIHELP — Hire a Live Human Expert MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_message.

What tools does the LIVEAIHELP — Hire a Live Human Expert MCP server have?

6 tools: 1 destructive, 1 irreversible, 3 write, 1 read. end_session, send_message, hire_human_expert, check_queue, check_balance and read_messages.

Does the LIVEAIHELP — Hire a Live Human Expert MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the LIVEAIHELP — Hire a Live Human Expert MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_message.

Has the LIVEAIHELP — Hire a Live Human Expert MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.