PromptQL MCP Server
About
Model Context Protocol (MCP) server for Hasura PromptQL
Details
- Author
- hasura
- GitHub stars
- 18
- Downloads
- 193
- Categories
- Other
Jump to
- Natural language data queries in plain English
- Table artifact support for formatted results
- Secure configuration for API credentials
- Dual authentication modes (public and private DDN)
- Data analysis and visualization insights
- Simple integration with MCP-compatible clients
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
PromptQL MCP ServerCommand (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 from source by cloning the repository, creating a Python 3.10+ virtual environment, and running pip install -e .. Configure credentials with python -m promptql_mcp_server setup (using flags for API key, playground URL, auth token, and auth mode) or via environment variables (PROMPTQL_API_KEY, PROMPTQL_PLAYGROUND_URL, PROMPTQL_AUTH_TOKEN, PROMPTQL_AUTH_MODE). For Claude Desktop, add the server to the MCP configuration JSON, pointing to the Python executable.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"promptql mcp server": {
"promptql-mcp": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}
}McpServers
{
"promptql-mcp": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}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)
- UsesAuth-Token header for authentication
- Compatible with public DDN endpoints
- Backward compatible with existing configurations
- Use when: Your DDN deployment is publicly accessible
Private Mode
- Usesx-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):
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
