Human Use

What is Human Use about?

Human Use provides a bridge between AI agents and human contributors. By exposing a set of MCP tools, it lets developers request short free‑text answers, image classifications, image rankings, and text comparisons directly from humans through the Rapidata platform.

How to use Human Use?

1. Clone the repository and copy .env.example to .env with your Rapidata credentials.
2. Install UV (or another Python package manager) and set up a virtual environment.
3. Run uv sync to install dependencies.
4. Launch the Streamlit UI with streamlit run app.py.
5. Optionally add the MCP server to Cursor by adding the provided JSON snippet to ~/.cursor/mcp.json.

Key Features of Human Use

• get_free_text_responses: obtain short, free‑form answers from real humans.
• get_human_image_classification: crowd‑source image labels.
• get_human_image_ranking: collect ranked order of images.
• get_human_text_comparison: let people choose the better of two texts.
• Ready‑to‑use Streamlit interface for quick testing.
• Hosted version available at chat.rapidata.ai for zero‑setup usage.

Use Cases of Human Use

• Enhancing generative AI outputs (e.g., refining car designs, slogans, function names).
• Validating and ranking image generation models.
• Human‑in‑the‑loop evaluation of text summarization or translation.
• Building interactive chatbots that can defer to human expertise when needed.

FAQ from the Human Use

Q: Do I need a Rapidata account? A: Yes, an API key from Rapidata is required and should be placed in the .env file.

Q: Can I run this without installing UV? A: You can use any Python package manager (pip, poetry, etc.) as long as dependencies are installed.

Q: Is there a hosted solution? A: Yes, the hosted instance is accessible at chat.rapidata.ai which provides all features without local setup.

Q: How does the MCP server integrate with Cursor? A: Add the provided JSON snippet to ~/.cursor/mcp.json; Cursor will then list the "human-use" server for selection.

🤖 Human Use is the easiest way to connect your AI agents with human intelligence via the Rapidata API.

Hosted Version

We now offer a hosted version of Human Use at chat.rapidata.ai - access all the features without setting up your own environment!

Human Use in Action

Coming up with a cool car design

https://github.com/user-attachments/assets/0d4c5c8f-4177-4fcf-8028-800dab16b009

Finding the best slogan

Function Naming

Ranking different image generation models.

MCP Server

Overview

The MCP server is a tool that allows you to connect your AI agents with human intelligence via the Rapidata API.

Tools

1. get_free_text_responses
   • Will ask actual humans to provide some short free text responses to the question.
2. get_human_image_classification
   • Will ask actual humans to classify the images in the directory.
3. get_human_image_ranking
   • Will ask actual humans to rank the images in the directory.
4. get_human_text_comparison
   • Will ask actual humans to compare two texts and select which one is better.

Configuration

Cursor

add the following to your cursor mcp.json file (usually in ~/.cursor/mcp.json)

{
    "mcpServers": {
        "human-use": {
            "command": "uv",
            "args": [
                "--directory",
                "YOUR_ABSOLUTE_PATH_HERE",
                "run",
                "rapidata_human_api.py"
            ]
        }
    }
}

You should now be able to see the human-use server in Cursor settings.

App

Overview

The app is a custom Streamlit app that allows you to use the MCP server. We have built because of issues with other clients. Namely the Claude desktop app.

App Setup

Clone Repository

git clone https://github.com/RapidataAI/human-use.git

Environment Configuration

Copy the .env.example file to .env and fill it in with your own credentials/settings

Note: paths should be ABSOLUTE paths

Installation with UV

Prerequisites

Install uv if you haven't already:

# For MacOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# For Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Setup Instructions (in the human-use repository)

1. Create and activate a virtual environment:

   uv venv
   
   # On Unix/macOS
   source .venv/bin/activate
   
   # On Windows
   .venv\Scripts\activate
   

2. Install dependencies:

   uv sync
   

Run the application

streamlit run app.py

Troubleshooting

If you encounter issues, with the dependencies make sure that "which python" and "which streamlit" are the same path. If they are not the same path, run "python -m streamlit run app.py" instead of "streamlit run app.py".

If UV is not found, make sure you close all terminals and editors, then re-open a new one and try again.

Contact

If you have any questions or need further assistance, please contact us at info@rapidata.ai.