Open Source

The declarative MCP framework.

The open-source framework for building MCP tool servers from declarative config. Define tools once and get auth, caching, and observability built in.

Star on GitHub Get started →
curl -fsSL /install | bash

Capabilities

Everything you need.
Nothing you don't.

From prototypes to multi-agent production systems — without changing your architecture.

Declarative Config

Define tools in YAML. Each directory under app/tools/ becomes one MCP tool — no manual registration or boilerplate.

Agent-Ready

Serve tools over Streamable HTTP. Any AI agent that speaks MCP can call your tools without custom integration.

Built-in Auth

Attach authentication to any tool with the built-in api_key plugin, or write your own. No global middleware to configure.

TypeScript Scripts

Add handlers and transforms when config alone isn't enough. Scripts run in a sandboxed runtime with fetch and console.

Caching

Enable tool result caching globally or per-tool with a TTL. Identical requests return cached results without hitting your database.

Multi-Database

Connect PostgreSQL, MySQL, MongoDB, and Redis. The framework manages pooling, health checks, and graceful shutdown.

Observability

Built-in OpenTelemetry tracing, metrics, and structured logging. Debug tool invocations end-to-end out of the box.

Compile & Deploy

Build compiles configs and scripts into a single artifact. Serve it anywhere — Docker, Kubernetes, bare metal, or any cloud.

How it works

Define. Build. Serve.

Go from idea to production MCP server in three steps. No application code required.

1

Define

Describe your tools, database connections, and authentication as declarative config. What each tool does, what it accepts, and who can call it.

2

Build

Hyperterse validates everything, bundles your config and scripts, and produces a single deployable artifact. Catch errors before they reach production.

3

Serve

Start a production-ready MCP server with auth, caching, and observability built in. Any AI agent that speaks MCP can connect immediately.

Why Hyperterse

Stop writing boilerplate.

Define tools once, get a production MCP server with auth, caching, and observability built in.

Without Hyperterse
  • Build MCP tool servers from scratch for each project
  • Write custom input validation and error handling
  • Implement auth, caching, and observability yourself
  • Manage database connections, pooling, and health checks manually
  • Weeks of development and ongoing maintenance
With Hyperterse
  • Define each tool in a YAML config file
  • Automatic input validation and type checking
  • Auth, caching, and OpenTelemetry observability built in
  • Framework handles pooling, health checks, and graceful shutdown
  • Up and running in minutes, not weeks

Open Source

Built in the open.

Hyperterse is free and open source under Apache 2.0. Star the repo, report issues, contribute features — the roadmap is shaped by the community.

Star on GitHub

or install now

curl -fsSL /install | bash

FAQ

Questions & answers.

What is Hyperterse?

Hyperterse is an open-source framework for building MCP (Model Context Protocol) tool servers from declarative YAML configuration. You define tools and database connections in config files, and Hyperterse compiles, validates, bundles, and serves them as a standards-compliant MCP server — with auth, caching, and observability built in.

Is Hyperterse free?

Yes. Hyperterse is free and open source under the Apache 2.0 license. You can self-host it on your own infrastructure at no cost. Enterprise support is available — reach out at enterprise@hyperterse.ai.

How does Hyperterse configuration work?

You define adapters (database connections) in app/adapters/ and tools in app/tools/. Each tool directory contains a config.terse file with a SQL statement, typed inputs, and optional auth and caching rules. Hyperterse uses the directory name as the MCP tool name automatically.

Which databases does Hyperterse support?

Hyperterse supports PostgreSQL, MySQL, MongoDB, and Redis out of the box. Each database uses its own adapter, and you can configure multiple connections in a single Hyperterse instance. Hyperterse manages connection pooling, health checks, and graceful shutdown.

What is MCP?

MCP (Model Context Protocol) is a standard for exposing tools to AI assistants and LLMs. Hyperterse serves tools over Streamable HTTP, so any AI agent that speaks MCP can call your tools via JSON-RPC 2.0.

Is my data secure with Hyperterse?

Yes. Connection strings and raw SQL are never exposed to clients. Hyperterse acts as a secure gateway — agents interact only with typed MCP tool interfaces, never with the underlying database directly. Hyperterse supports per-tool authentication using the built-in api_key plugin or custom auth plugins.

Does Hyperterse require writing code?

Not for most tools. Hyperterse is configuration-driven: write SQL queries in .terse files and serve them. For advanced use cases — like custom validation, data transformation, or non-database logic — Hyperterse supports optional TypeScript handlers that run in a sandboxed runtime.

Is Hyperterse an ORM?

No. Hyperterse doesn't abstract away SQL — you write raw queries directly in your config. Hyperterse focuses on serving database queries as MCP tools with production-grade infrastructure, not on database abstraction or migrations.