Hyperterse

Hyperterse is a high-performance runtime server that transforms database queries into RESTful API endpoints and MCP (Model Context Protocol) tools. It provides the interface between production databases and AI agents, allowing developers to define queries in a simple configuration file and automatically generate endpoints with full OpenAPI documentation, input validation, and AI integration capabilities. The tool is designed to support everything from prototypes to multi-agent systems without requiring changes to your architecture.

• Declarative Data Interfaces - Define the shape and intent of data access once, and let Hyperterse handle execution, validation, and exposure automatically.

• Agent-Ready by Design - Connect your data to AI agents through discoverable, callable tools without exposing SQL, schemas, or credentials to clients.

• Zero-Boilerplate APIs - Turn queries into production-ready APIs with typed inputs, predictable outputs, and built-in documentation with no code required.

• Single Source of Truth - Generate endpoints, OpenAPI specs, LLM-readable docs, and MCP tools from one configuration file.

• Security as a Baseline - Keep raw SQL, connection strings, and internal errors fully contained within the runtime, acting as a secure gateway.

• Database Independence - Work across PostgreSQL, MySQL, and Redis using a consistent, unified interface.

• MCP Integration - Automatically generates MCP-compatible tools for each query, allowing AI agents to execute database queries via JSON-RPC 2.0.

• Auto-Generated Documentation - Creates OpenAPI 3.0 specifications, markdown documentation at /llms.txt for LLM integration, and agent skills archives.

To get started, install Hyperterse via npm (npm i -g hyperterse), Bun (bun add -g hyperterse), Brew (brew install hyperterse/tap/hyperterse), or curl. Define your queries in a configuration file (e.g., config.terse), specifying adapters for database connections, queries with SQL statements, and input parameters with their types. Run the server and Hyperterse handles the rest—generating endpoints at POST /query/{query-name}, validating inputs, and creating documentation automatically.