Koskamo

LiveAIHelp MCP

This MCP server enables AI agents to hire vetted human experts for live video or chat assistance when the agent encounters tasks it cannot perform, such as using websites, making judgment calls, or verifying real-world conditions. It provides tools to hire experts, send and read messages, check queue status, end sessions, and manage billing balances.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

LiveAIHelp MCP logo, by LIVEAIHELPVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by LIVEAIHELP
You need:Create an API key: sign up at https://www.helpai.live/signup, then Portal → "API keys for bots".
MCP endpoint (Streamable HTTP)
https://www.helpai.live/api/mcp
Vendor documentation

What you can do with it

  • Hire a human expert for technical support or guidance
  • Send messages to a live expert session
  • Check queue position and session status
  • End a session to stop billing

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
liveaihelp 1.0.0
MCP protocol
2025-06-18
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Tools

6 advertised

hire_human_expert — Hire a human expert
Advertised by the server during the last successful anonymous check.
Open-world

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.

hire_human_expert input schema
{
  "type": "object",
  "required": [
    "topic"
  ],
  "properties": {
    "mode": {
      "enum": [
        "chat",
        "video"
      ],
      "type": "string",
      "description": "Session mode. Defaults to chat."
    },
    "topic": {
      "type": "string",
      "description": "What you need help with. Be specific — this is shown to the expert."
    }
  }
}
hire_human_expert annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
send_message — Send a message to the expert
Advertised by the server during the last successful anonymous check.
Open-world

Send a chat message to the human expert in an active session. You are the customer in this conversation.

send_message input schema
{
  "type": "object",
  "required": [
    "session_id",
    "message"
  ],
  "properties": {
    "message": {
      "type": "string",
      "description": "Message text to send to the expert."
    },
    "session_id": {
      "type": "string",
      "description": "The session_id from hire_human_expert."
    }
  }
}
send_message annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
read_messages — Read expert messages
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

read_messages input schema
{
  "type": "object",
  "required": [
    "session_id"
  ],
  "properties": {
    "after": {
      "type": "string",
      "description": "ISO timestamp — only return messages after this time. Omit on first call."
    },
    "session_id": {
      "type": "string",
      "description": "The session_id from hire_human_expert."
    }
  }
}
read_messages annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
check_queue — Check queue position
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Check your position in the expert holding queue. Poll until status is matched, then use the returned session_id with send_message / read_messages.

check_queue input schema
{
  "type": "object",
  "required": [
    "queue_id"
  ],
  "properties": {
    "queue_id": {
      "type": "string",
      "description": "The queue_id from hire_human_expert."
    }
  }
}
check_queue annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
end_session — End session
Advertised by the server during the last successful anonymous check.
Advertised destructiveOpen-world

End the session when the task is done. This stops billing immediately. Always call this when you are finished.

end_session input schema
{
  "type": "object",
  "required": [
    "session_id"
  ],
  "properties": {
    "session_id": {
      "type": "string",
      "description": "The session_id to end."
    }
  }
}
end_session annotations
{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": true
}
check_balance — Check minute balance
Advertised by the server during the last successful anonymous check.
Advertised read-only

Check the minute balance of the connected LIVEAIHELP account.

check_balance input schema
{
  "type": "object",
  "properties": {}
}
check_balance annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
625 ms
95th percentile latency
625 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 625 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http liveaihelp-mcp https://www.helpai.live/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add liveaihelp-mcp --url https://www.helpai.live/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable liveaihelp-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "liveaihelp-mcp": {
      "url": "https://www.helpai.live/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "liveaihelp-mcp": {
      "type": "streamableHttp",
      "url": "https://www.helpai.live/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start liveaihelp-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "liveaihelp-mcp": {
      "type": "http",
      "url": "https://www.helpai.live/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http liveaihelp-mcp https://www.helpai.live/api/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "liveaihelp-mcp": {
      "url": "https://www.helpai.live/api/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "liveaihelp-mcp": {
      "serverUrl": "https://www.helpai.live/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like LiveAIHelp MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run LiveAIHelp MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing