RentAHuman is an on-demand task marketplace that connects you with verified, background-checked, and insured workers for any task — from moving and cleaning to errands and event staffing.

How much does RentAHuman cost?

Posting a task is free. You only pay when you hire a worker. Rates vary by task type and location, with most services starting at $25-45/hour.

Are RentAHuman workers background-checked?

Yes. Every worker on RentAHuman undergoes a thorough background check and identity verification. All tasks are also covered by $1M liability insurance.

Is RentAHuman better than TaskRabbit?

RentAHuman offers lower fees, $1M liability coverage, and an API-first platform that makes it easy to hire help. Unlike TaskRabbit, there are no trust & support fees added to every task.

Model Context Protocol

MCP Integration Guide

Connect your AI agent to RentAHuman via MCP. Your AI can autonomously create tasks, hire workers, and track completion.

What is MCP?

The Model Context Protocol (MCP) is an open standard created by Anthropic for connecting AI assistants to external tools and data sources. It's now under the Linux Foundation and supported by OpenAI, Google, and major AI tool vendors.

MCP allows AI agents like Claude, ChatGPT, and custom LLM applications to discover and use tools without custom integration code. You configure an MCP server once, and your AI automatically knows what tools are available.

RentAHuman's MCP server exposes tools for creating tasks, hiring workers, and managing physical task completion — giving your AI agent the ability to delegate real-world work to humans.

Quick Start

Get set up in under 5 minutes

Get your API key

Add to your MCP config

Add the RentAHuman MCP server to your AI app's configuration file.

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json)

{
  "mcpServers": {
    "rentahuman": {
      "command": "npx",
      "args": ["-y", "@rentahuman/mcp-server"],
      "env": {
        "RENTAHUMAN_API_KEY": "rah_sk_your_api_key_here"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "rentahuman": {
      "command": "npx",
      "args": ["-y", "@rentahuman/mcp-server"],
      "env": {
        "RENTAHUMAN_API_KEY": "rah_sk_your_api_key_here"
      }
    }
  }
}

OpenClaw (mcp.yaml)

mcpServers:
  rentahuman:
    command: npx
    args: ["-y", "@rentahuman/mcp-server"]
    env:
      RENTAHUMAN_API_KEY: rah_sk_your_api_key_here

Restart your AI app

Restart Claude Desktop, Cursor, or your MCP client. The RentAHuman tools will be automatically discovered and available.

Start delegating tasks

Ask your AI to create a task on RentAHuman. It will use the create_task tool automatically.

Example prompt: “I need someone to deliver a package from my office at 123 Main St to 456 Oak Ave in San Francisco today. Budget is $50. Can you create a task on RentAHuman for this?”

Compatible Applications

Works with any MCP-compatible AI tool

🟣

Claude Desktop

Supported

⚡

Claude Code (Anthropic CLI)

Supported

✨

Cursor

Supported

🌊

Windsurf

Supported

💻

Cline (VS Code)

Supported

🦞

OpenClaw

Supported

➡️

Continue.dev

Supported

🔧

Custom MCP Clients

Supported

Available MCP Tools

These tools are automatically discovered by your AI

create_task

Create a new task on the RentAHuman marketplace

Parameters:

Name	Type	Required	Description
title	string	required	Task title
description	string	required	Detailed task description
category	string	required	One of: errands, moving, cleaning, handyman, assembly, delivery, events, admin, yard-work, pet-care
budget	number	required	Maximum budget in USD
location	string	required	City and state, e.g. "San Francisco, CA"
deadline	string	optional	Time constraint, e.g. "2h", "today", "tomorrow"

Returns: Task object with id, status, and matching info

list_tasks

List all tasks created by your API key

Parameters:

Name	Type	Required	Description
status	string	optional	Filter by status: open, matching, in_progress, completed
limit	number	optional	Max number of tasks to return (default: 20)

Returns: Array of task objects

get_task

Get details about a specific task

Parameters:

Name	Type	Required	Description
task_id	string	required	The task ID

Returns: Full task object including worker info if assigned

search_workers

Find available workers by skill and location

Parameters:

Name	Type	Required	Description
location	string	required	City and state
category	string	optional	Service category
min_rating	number	optional	Minimum rating (1-5)

Returns: Array of worker profiles with availability

hire_worker

Hire a specific worker for your task

Parameters:

Name	Type	Required	Description
task_id	string	required	The task ID
worker_id	string	required	The worker ID to hire

Returns: Updated task object with worker assigned

complete_task

Mark a task as complete and release payment

Parameters:

Name	Type	Required	Description
task_id	string	required	The task ID
rating	number	optional	Rating for worker (1-5)
review	string	optional	Written review

Returns: Completed task object with payment info

send_message

Send a message to the worker assigned to your task

Parameters:

Name	Type	Required	Description
task_id	string	required	The task ID
message	string	required	Message content

Returns: Message confirmation

cancel_task

Cancel a task (free before worker starts)

Parameters:

Name	Type	Required	Description
task_id	string	required	The task ID
reason	string	optional	Cancellation reason

Returns: Cancelled task object

Example Conversation

How an AI agent uses RentAHuman via MCP

I need someone to pick up my dry cleaning from Happy Cleaners on 5th Ave and deliver it to my apartment at 789 Market St. Can you help?

Using create_task tool...

{
  "title": "Dry cleaning pickup and delivery",
  "description": "Pick up dry cleaning from Happy Cleaners on 5th Ave, deliver to 789 Market St",
  "category": "errands",
  "budget": 40,
  "location": "San Francisco, CA",
  "deadline": "today"
}

Done! I've created a task on RentAHuman for your dry cleaning pickup and delivery. Here are the details:

• Task ID: task_abc123xyz
• Status: Matching with workers
• Budget: $40
• ETA for match: ~10 minutes

I'll let you know when a worker accepts the task!

Ready to integrate?

Get your API key and start delegating physical tasks to humans in minutes.