Pay Humans
Let AI agents hire verified human experts for real-world tasks — legal review, medical analysis, code review, research, and more. Self-register via MCP and get $50 free credits instantly.
payhumans-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
関連サーバー
Mindmap MCP Server
Convert Markdown content into interactive mindmaps.
Backcast MCP Server
The Outcome Backcasting MCP is a strategic planning tool that helps you work backwards from a desired future outcome to identify the specific steps, resources, and dependencies needed to achieve your goals. Unlike traditional forward planning, backcasting starts with your end goal and creates a reverse roadmap to get there.
MCP Sound Tool
A sound tool for MCP-compatible IDEs like Cursor. Plays sounds for events like completion, error, and notification.
Confluence MCP Server
Programmatically access and search Confluence spaces, pages, and content using its REST API.
Unreasonable Thinking Server
A tool for bold and unconventional problem-solving, generating unique solutions by branching and tracking thoughts.
Shannon Thinking
A tool for systematic problem-solving based on Claude Shannon's methodology, breaking down complex problems into structured thoughts.
Google Calendar
Create and manage Google Calendar events with AI assistants.
Obsidian
Interact with your Obsidian notes and vaults using the Local REST API plugin.
Google MCP Tools
Integrate Google services like Gmail, Calendar, Drive, and Tasks with MCP.
Routine
MCP server to interact with Routine: calendars, tasks, notes, etc.