What does the Pay Humans MCP server do?
It acts as a bridge between AI agents (like Claude) and the Pay Humans platform, exposing tools for agents to search for, hire, and communicate with human experts, and to manage job lifecycle.
@Krishnan-govindan
基本情報
The human API for AI agents. When your agent hits a task it can't do — verify a fact, review a contract, analyze medical data, check code quality, evaluate a design — PayHumans matches it with a vetted domain expert who completes the task and returns the result.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"payhumans": {
"url": "https://vepblpimledbyxwydihz.supabase.co/functions/v1/mcp"
}
}
}Find human experts by domain, research type, or max rate
Post a new job for a human expert to complete
Fetch job status and results
List your agent's jobs (optional status filter)
Accept expert's work and trigger payout
Send a message to the assigned expert
Get an expert's full profile, availability, and rating
Pay Humans is an MCP (Model Context Protocol) server that connects AI agents to the Pay Humans platform, allowing them to discover and hire human experts for tasks the agent cannot complete alone—such as research, verification, physical delivery, and expert calls.
Install the server via Smithery (npx -y @smithery/cli install payhumans-mcp --client claude) or directly with npx -y payhumans-mcp. Set the AGENT_API_KEY environment variable (key starts with ph_). Configure your MCP client (e.g., Claude Desktop or Claude Code) with the server command and API key, then use the provided tools to search experts, post jobs, and manage tasks.
It acts as a bridge between AI agents (like Claude) and the Pay Humans platform, exposing tools for agents to search for, hire, and communicate with human experts, and to manage job lifecycle.
Yes. You must set the `AGENT_API_KEY` environment variable with a key starting with `ph_`, obtainable at payhumans.io.
The README provides configurations for Claude Desktop (via `claude_desktop_config.json`) and Claude Code (via `claude mcp add`).
The agent posts a job via `post_job`, the platform matches it to an expert, the expert completes it, the agent reviews via `get_job` and accepts via `complete_job`, then the expert is paid automatically.
All data is handled through the Pay Humans API (default endpoint `https://api.payhumans.io`). The server itself only proxies requests.

Agent-Native Terminal

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

Turn a plain-language guide into a narrated walkthrough video of your deployed web app. Your coding agent can write the guide from the source and bring back the MP4.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
コメント