LIVEAIHELP — Hire a Live Human Expert
Server Details
Hire a vetted human expert live via chat or video when your AI agent gets stuck. $1/min.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- liveaihelp/liveaihelp-mcp
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool targets a distinct action in the session lifecycle: starting a hire, polling queue status, sending/reading chat, checking balance, and ending a session. The descriptions explicitly clarify the boundary between hire_human_expert (initiates session or queues) and check_queue (polls position), preventing misselection.
All six tools follow a strict verb_noun snake_case convention (check_balance, check_queue, end_session, hire_human_expert, read_messages, send_message). No mixing of styles or vague verbs.
Six tools is well-scoped for a hire/message/end-session workflow, with each tool earning its place. Nothing feels redundant or missing at the count level.
Core lifecycle (hire, queue polling, messaging, balance, end session) is covered end-to-end. Minor gaps exist: no explicit cancel_session, and session status is only surfaced indirectly via read_messages or check_queue rather than a dedicated status tool.
Available Tools
6 toolscheck_balanceCheck minute balanceARead-onlyIdempotentInspect
Check the minute balance of the connected LIVEAIHELP account.
Inputs: no named parameters.
check_queueCheck queue positionARead-onlyIdempotentInspect
Check your position in the expert holding queue. Poll until status is matched, then use the returned session_id with send_message / read_messages.
Inputs: queue_id (required).
end_sessionEnd sessionADestructiveInspect
End the session when the task is done. This stops billing immediately. Always call this when you are finished.
Inputs: session_id (required).
hire_human_expertHire a human expertAInspect
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.
Inputs: topic (required), mode.
read_messagesRead expert messagesARead-onlyIdempotentInspect
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.
Inputs: session_id (required), after.
send_messageSend a message to the expertAInspect
Send a chat message to the human expert in an active session. You are the customer in this conversation.
Inputs: message (required), session_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Let your AI agent hire a human for tasks it can't do — first post free.
Real humans for AI agents: ask a question or rent a human for a task. Prepaid in EUR.
Human-as-a-Service for AI agents. Delegate tasks that need a real human, get results via API.
Find and hire a human specialist from the Stoory marketplace, right from chat.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceLets AI agents natively discover and hire human experts for tasks they can't do themselves, such as research, verification, and expert calls.MIT
- AlicenseAqualityBmaintenanceLast-mile human work for AI agents. Phone calls, physical-world tasks, captcha on an already-authorized account, subjective QA, and long manual work, done by real virtual assistants.1374 npmMIT
- AlicenseNot gradedqualityCmaintenanceDelegates real-world digital tasks to vetted humans directly from AI chat. Provides tools to get quotes, post tasks, and check status with escrow protection.22 npmMIT

humanforaiofficial
AlicenseAqualityCmaintenanceEnables AI agents to hire real human operators for tasks requiring physical presence, human perception, or judgment, such as verification, testing, data collection, and physical-world tasks.446 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.