Payhumans MCP Server

MCP server for Pay Humans — lets AI agents hire human experts

Local serverstdio

What is the Payhumans MCP MCP server?

Connect Payhumans MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server for Pay Humans — lets AI agents hire human experts. The payhumans mcp mcp server is what makes that connection.

What the server does

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.

Installation

The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • 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

Credentials and setup notes

Configuration is passed through the environment: AGENT_API_KEY, API_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Payhumans MCP's toolset — search_experts, post_job, get_job and 4 more — is a fair guide to whether it matches your workflow. It is maintained by krishnan-govindan; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
search_expertsFind human experts by domain, research type, or max rate
post_jobPost a new job for a human expert to complete
get_jobFetch job status and results
list_jobsList your agent's jobs (optional status filter)
complete_jobAccept expert's work and trigger payout
send_messageSend a message to the assigned expert
get_expertGet an expert's full profile, availability, and rating

How to install the Payhumans MCP MCP server

{
  "mcpServers": {
    "payhumans": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "AGENT_API_KEY": "your-value",
        "API_BASE_URL": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
AGENT_API_KEYCredential the server authenticates with.Yes
API_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Payhumans MCP to search experts.
  • Use Payhumans MCP to post job.
  • Use Payhumans MCP to get job.

Frequently asked questions

It connects Payhumans MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (search_experts, post_job, get_job, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Payhumans MCP directly.