Humanrail
About
MCP server for HumanRail — route tasks requiring human judgment to vetted workers from any AI agent
Details
- Author
- prime001
- Downloads
- 286
- Categories
- Other, AI, Automation
Jump to
- Routes tasks to a curated human worker pool
- Pays workers instantly via Lightning Network
- 6‑stage verification pipeline validates every result
- Define expected output with JSON Schema
- Pay‑per‑task pricing with no subscriptions
- Supports custom task types and common use cases
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
HumanrailCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install with pip install humanrail-mcp-server or run directly with uvx humanrail-mcp-server. Configure your API key in the environment variable HUMANRAIL_API_KEY (get one at humanrail.dev) and add the server to your Claude Code or Claude Desktop config. Once connected, your AI agent can use tools like create_task, get_task, and wait_for_task to route and retrieve human‑reviewed results.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"humanrail": {
"humanrail": {
"command": "uvx",
"args": [
"humanrail-mcp-server"
],
"env": {
"HUMANRAIL_API_KEY": "your-api-key"
}
}
}
}
}McpServers
{
"humanrail": {
"command": "uvx",
"args": [
"humanrail-mcp-server"
],
"env": {
"HUMANRAIL_API_KEY": "your-api-key"
}
}
}HumanRail MCP Server
Route tasks requiring human judgment to a vetted worker pool — directly from any AI agent.
When your AI agent hits something it can't handle — content moderation, refund decisions, subjective quality assessments, data verification — HumanRail routes it to a human worker, verifies the result, pays the worker via Lightning Network, and returns structured output.
Think "Stripe for human judgment."
Quick Start
Install
pip install humanrail-mcp-server
Or run directly:
uvx humanrail-mcp-server
Configure
Add to your Claude Code config (~/.claude.json):
{
"mcpServers": {
"humanrail": {
"command": "uvx",
"args": ["humanrail-mcp-server"],
"env": {
"HUMANRAIL_API_KEY": "ek_live_your_key_here"
}
}
}
}
Or for Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"humanrail": {
"command": "uvx",
"args": ["humanrail-mcp-server"],
"env": {
"HUMANRAIL_API_KEY": "ek_live_your_key_here"
}
}
}
}
Get an API Key
Sign up at humanrail.dev to get your API key.
Available Tools
| Tool | Description |
|------|-------------|
| create_task | Route a task to a human worker for review/judgment |
| get_task | Check the status and result of a task |
| wait_for_task | Poll until a task completes (blocking) |
| cancel_task | Cancel a pending task |
| list_tasks | List tasks with filters (status, type, date range) |
| get_usage | View usage stats and billing summary |
| health_check | Check if the HumanRail API is reachable |
Example Usage
Once connected, Claude can use HumanRail naturally:
> User: "Review this customer's refund request — order #12345, they say the item arrived damaged."
>
> Claude: I'll route this to a human reviewer for a refund eligibility decision.
> (calls create_task with task_type="refund_eligibility")
>
> The human reviewer has verified: Refund approved. The item shows visible damage in the photos and the customer's account is in good standing.
Task Types
You can create any task type. Common examples:
- content_moderation — Is this content appropriate?
- refund_eligibility — Should we approve this refund?
- data_verification — Is this information accurate?
- quality_assessment — Rate this output 1-10
- document_review — Extract/verify information from a document
- sentiment_analysis — What's the tone/intent of this message?
Output Schema
Define exactly what you need back using JSON Schema:
```python
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
