Introduction

Hyperterse is a high-performance runtime server that transforms database queries into REST endpoints and MCP tools. Define queries in a configuration file and Hyperterse handles execution, validation, documentation, and AI integration.

Why Hyperterse?

Hyperterse is designed for AI-first applications. It serves multiple use cases, and is aimed to simplify the integration of your database with AI agents, LLMs or other systems.

Agent-ready by design Connect your data to AI agents through discoverable, callable tools—without exposing SQL, schemas, or credentials.

Zero-boilerplate APIs Turn queries into production-ready APIs with typed inputs, predictable outputs, and built-in documentation.

Single source of truth Generate REST endpoints, OpenAPI specs, LLM-readable docs, and MCP tools from one configuration file.

Database independence Work across PostgreSQL, MySQL, and Redis using a consistent, unified interface.

How it works

Define your queries once in a simple configuration file:

config.terse

name: my-api

adapters:
  production_db:
    connector: postgres
    connection_string: 'postgresql://user:pass@host:5432/db'

queries:
  get-user:
    use: production_db
    description: 'Retrieve a user by email address'
    statement: |
      SELECT id, name, email, created_at
      FROM users
      WHERE email = {{ inputs.email }}
    inputs:
      email:
        type: string
        description: 'User email address'

Run the server:

hyperterse run -f config.terse

Call your query via REST or MCP:

curl -X POST http://localhost:8080/query/get-user \
  -H "Content-Type: application/json" \
  -d '{"email": "user@example.com"}'

What’s included

• REST Endpoints: Each query becomes its own REST endpoint
• MCP Protocol: JSON-RPC 2.0 tools
• OpenAPI Docs: Auto-generated
• LLM Documentation: AI-friendly
• Input Validation: Strong typing and validation by default
• Security: Connection strings and raw SQL never exposed to clients
• Hot reloading: Development mode with automatic reload on configuration changes