PromptQL MCP Server logo

PromptQL MCP Server

by Hasura

Connect Hasura PromptQL to AI assistants like Claude using the Model Context Protocol (MCP). This allows AI assistants to directly query your enterprise data using natural language.

View on GitHub

Last updated: N/A

What is PromptQL MCP Server?

A bridge between Hasura's PromptQL data agent and AI assistants through the Model Context Protocol (MCP). It allows AI assistants to query enterprise data using natural language, leveraging PromptQL's capabilities.

How to use PromptQL MCP Server?

Install the server from source using pip. Configure your PromptQL credentials using the setup command. Then, run the server and configure your MCP-compatible client (e.g., Claude Desktop) to connect to the server. Use natural language prompts to query your data.

Key features of PromptQL MCP Server

  • Natural Language Data Queries

  • Table Artifact Support

  • Secure Configuration

  • Data Analysis

Use cases of PromptQL MCP Server

  • Querying sales data

  • Identifying top customers

  • Analyzing user signup trends

  • Determining product profit margins

FAQ from PromptQL MCP Server

What is PromptQL?

Hasura's Natural Language API for data access and analysis.

What is MCP?

Model Context Protocol, a standard for connecting AI models to external tools and data.

What AI assistants are compatible?

Claude Desktop and any MCP-compatible client.

How do I configure the server?

Use the python -m promptql_mcp_server setup command with your API key and DDN URL.

What tools are available?

The server exposes the ask_question, setup_config, and check_config MCP tools.