About Pay Humans
An MCP server for the Pay Humans platform, where AI agents can find and hire human experts for tasks they cannot complete themselves. It also supports job follow-up, expert profile lookup, and accepting work to trigger payment.
Key features
- 01Search experts by domain and rate
- 02Post expert jobs
- 03Check job status and results
- 04View expert profiles and availability
- 05Message experts and accept work
Use cases
- 01Delegate fact-checking to an expert
- 02Find specialists for research
- 03Track jobs and review results
- 04Accept expert work and trigger payment
MCP support
It exposes tools for finding experts, posting and tracking jobs, viewing expert profiles, messaging experts, and accepting completed work to MCP clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://vepblpimledbyxwydihz.supabase.co/functions/v1/mcpclaude mcp add --transport http payhumans https://vepblpimledbyxwydihz.supabase.co/functions/v1/mcp{"mcpServers":{"payhumans":{"type":"http","url":"https://vepblpimledbyxwydihz.supabase.co/functions/v1/mcp"}}}Open in Cursor{"servers":{"payhumans":{"type":"http","url":"https://vepblpimledbyxwydihz.supabase.co/functions/v1/mcp"}}}Open in VS Code{"mcpServers":{"payhumans":{"type":"http","url":"https://vepblpimledbyxwydihz.supabase.co/functions/v1/mcp"}}}{"mcpServers":{"payhumans":{"serverUrl":"https://vepblpimledbyxwydihz.supabase.co/functions/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEpayhumans-mcp
MCP (Model Context Protocol) server for the Pay Humans platform. Lets AI agents natively discover and hire human experts for tasks they can't do themselves -- research, verification, physical delivery, expert calls, and more.
Tools
| Tool | Description |
|---|---|
search_experts | Find human experts by domain, research type, or max rate |
post_job | Post a new job for a human expert to complete |
get_job | Fetch job status and results |
list_jobs | List your agent's jobs (optional status filter) |
complete_job | Accept expert's work and trigger payout |
send_message | Send a message to the assigned expert |
get_expert | Get an expert's full profile, availability, and rating |
Install
Via Smithery (Recommended)
Install automatically via Smithery:
npx -y @smithery/cli install payhumans-mcp --client claude
Via npx
npx -y payhumans-mcp
Manual Install
npm install -g payhumans-mcp
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
AGENT_API_KEY | Yes | Your Pay Humans API key (starts with ph_) |
API_BASE_URL | No | API endpoint (default: https://api.payhumans.io) |
Get your API key at payhumans.io.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"payhumans": {
"command": "npx",
"args": ["-y", "payhumans-mcp"],
"env": {
"AGENT_API_KEY": "ph_your_key_here"
}
}
}
}
Claude Code
claude mcp add payhumans -- npx -y payhumans-mcp
Then set your API key:
export AGENT_API_KEY=ph_your_key_here
Example Usage
Once connected, your AI agent can:
"Search for healthcare experts on Pay Humans"
"Post a job to find someone who can verify a business address in San Francisco, budget $50"
"Check the status of my job"
"Find an expert in FDA regulations for an expert call, max $100/hr"
How It Works
AI Agent (Claude, GPT-4, etc.)
|
v
payhumans-mcp (this server)
|
v
Pay Humans API
|
v
Human Expert completes the task
|
v
Result returned to AI Agent
- Agent posts a job via
post_jobwith title, description, domain, budget - Platform matches the job to qualified human experts
- Expert completes the work and submits results
- Agent reviews via
get_joband accepts viacomplete_job - Expert gets paid automatically
Development
git clone https://github.com/Prithvi100/payhumans-mcp.git
cd payhumans-mcp
npm install
npm run dev
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.