Promptql MCP

🚀 PromptQL MCP Server

Connect Hasura PromptQL to AI assistants like Claude using the Model Context Protocol (MCP) for integration.

🚀 Quick Start

1. Configure PromptQL credentials:

python -m promptql_mcp_server setup --api-key YOUR_PROMPTQL_API_KEY --ddn-url YOUR_DDN_URL

2. Test the server:

python -m promptql_mcp_server

3. Interact with the server using the example client (located in the examples folder).

✨ Features

• 🔍 Natural Language Data Query - Ask questions about your enterprise data in plain English.
• 📊 Table Support - Get formatted table results.
• 🔐 Security Configuration - Securely store and manage PromptQL API credentials.
• 📈 Data Analysis - Gain data insights and visualizations.
• 🛠️ Easy Integration - Use with Claude Desktop and other MCP-compatible clients.

📦 Installation

Prerequisites

• Python 3.10 or higher.
• A Hasura PromptQL project with an API key and DDN URL.
• Claude Desktop (for interactive operations) or other MCP-compatible clients.

Install from Source

1. Clone the repository:

git clone https://github.com/hasura/promptql-mcp.git
cd promptql-mcp

2. Set up a virtual environment (recommended):

# Create a virtual environment
python -m venv venv

# Activate the virtual environment
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install the package:

pip install -e .

💻 Usage Examples

Basic Usage

from promptql_mcp_server.server import MCPServer

server = MCPServer()
server.run()

Advanced Usage

import requests

response = requests.post('http://localhost:5000/query', json={
    "model": "claude-2",
    "messages": [
        {
            "role": "user",
            "content": "告诉我今天的天气如何？"
        }
    ]
})
print(response.json())

📚 Documentation

For the complete API documentation and more detailed information, please refer to DOCS.md in the project repository.

🤝 Contribution

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -m 'Add some amazing features').
4. Push to the branch (git push origin feature/amazing-feature).
5. Open a Pull Request.

📄 License

This project is licensed under the MIT License. Please see the LICENSE file for details.

🙏 Acknowledgments

• Hasura for creating PromptQL.
• Anthropic for developing the Model Context Protocol.