PromptQL MCP Server

Status: Unstable and only for PromptQL v1. Alpha release coming soon for PromptQL v2.

Overview

This project provides a bridge between Hasura’s PromptQL data agent and AI assistants through the Model Context Protocol. With this integration, AI assistants can directly query your enterprise data using natural language, leveraging PromptQL’s powerful capabilities for data access, analysis, and visualization.

Features

• 🔍 Natural Language Data Queries - Ask questions about your enterprise data in plain English
• 📊 Table Artifact Support - Get formatted table results from your data queries
• 🔐 Secure Configuration - Safely store and manage your PromptQL API credentials
• 🔑 Dual Authentication Modes - Support for both public and private DDN deployments
• 📈 Data Analysis - Get insights and visualizations from your data
• 🛠️ Simple Integration - Works with Claude Desktop and other MCP-compatible clients

Authentication Modes

The PromptQL MCP server supports two authentication modes to work with different DDN deployment types:

Public Mode (Default)

• Uses Auth-Token header for authentication
• Compatible with public DDN endpoints
• Backward compatible with existing configurations
• Use when: Your DDN deployment is publicly accessible

Private Mode

• Uses x-hasura-ddn-token header for authentication
• Compatible with private DDN endpoints
• Enhanced security for private deployments
• Use when: Your DDN deployment is private/internal

You can specify the authentication mode during configuration using the --auth-mode flag or auth_mode parameter.

Installation

Prerequisites

• Python 3.10 or higher
• A Hasura PromptQL project with API key, playground URL, and DDN Auth Token
• Claude Desktop (for interactive use) or any MCP-compatible client

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 .

Quick Start

1. Configure your PromptQL credentials:

# For public DDN deployments (default)
python -m promptql_mcp_server setup --api-key YOUR_PROMPTQL_API_KEY --playground-url YOUR_PLAYGROUND_URL --auth-token YOUR_AUTH_TOKEN --auth-mode public

# For private DDN deployments
python -m promptql_mcp_server setup --api-key YOUR_PROMPTQL_API_KEY --playground-url YOUR_PLAYGROUND_URL --auth-token YOUR_AUTH_TOKEN --auth-mode private

Alternative: Environment Variables

export PROMPTQL_API_KEY="your-api-key"
export PROMPTQL_PLAYGROUND_URL="your-playground-url"
export PROMPTQL_AUTH_TOKEN="your-auth-token"
export PROMPTQL_AUTH_MODE="public"  # or "private"

2. Test the server: