- Updated: February 24, 2026
- 5 min read
Introducing Hyperterse: Open‑Source Declarative MCP Framework
Star on GitHub Get started → Open Source The declarative MCP framework. The open-source framework for building MCP tool servers declaratively. Define tools once and get auth, caching, and observability built in. No glue code. Star on GitHub Get started → cURL NPM Bun Brew curl -fsSL /install | bash npm i -g hyperterse bun add -g hyperterse brew install hyperterse/tap/hyperterse Capabilities Everything you need.Nothing you don’t.From prototypes to multi-agent production systems — without changing your architecture. Two-Tool Interface Agents see exactly two MCP tools — search and execute. Define hundreds of tools behind them; the agent discovers what it needs dynamically. Declarative Config Define tools in declaration files. Each directory under app/tools/ becomes a tool the agent can search for and execute — no registration code.Built-in Auth Attach authentication to any tool with the built-in api_key plugin, or write your own. Auth runs before every execute call automatically. TypeScript Scripts Add handlers and transforms when declaration files alone aren’t enough. Scripts run in a sandboxed runtime with fetch and console. Caching Enable result caching globally or per-tool with a TTL. Identical execute calls 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 every search and execute call end-to-end. Compile & Deploy Build compiles your declaration files and scripts into a single artifact. Serve it anywhere — Docker, Kubernetes, bare metal, or any cloud. How it works Define. Build. Serve.Every Hyperterse server exposes exactly two MCP tools, no matter how many you define behind it. Agents discover and run your tools through a single, consistent interface. 1 Define Describe your tools, database connections, and authentication in declaration files. Add as many as you need — Hyperterse compiles them into a single artifact. Search The agent calls search with a natural-language query.Hyperterse ranks your tools by metadata — name, description, statement, inputs — and returns the best matches. Execute The agent picks a tool and calls execute with structured inputs. Hyperterse handles auth, validation, caching, and observability — then returns the result. Why Hyperterse Stop writing boilerplate. Traditional MCP servers expose every tool individually. Hyperterse collapses them all behind search and execute — agents discover what they need, then run it.Without Hyperterse Every tool is a separate MCP endpoint the agent must know about Tool catalog bloats the agent’s context window Write custom input validation and error handling Implement auth, caching, and observability yourself Manage database connections, pooling, and health checks manually Adding tools means updating the agent’s integration Weeks of development and ongoing maintenance With Hyperterse Agents see two tools: search and execute Tools discovered dynamically — no context window bloat Define each tool in declaratively Automatic input validation and type checking Auth, caching, and OpenTelemetry observability built in Framework handles pooling, health checks, and graceful shutdown Add 100 tools — agents still connect the same way Open Source Built in the open. Hyperterse is free and open source under Apache 2.0. Two tools, unlimited possibilities. Star the repo, report issues, contribute features — the roadmap is shaped by the community. Star on GitHub or install now cURL NPM Bun Brew curl -fsSL /install | bash npm i -g hyperterse bun add -g hyperterse brew install hyperterse/tap/hyperterse FAQ Questions & answers. What is Hyperterse? Hyperterse is an open-source framework for building MCP (Model Context Protocol) tool servers from declaration files. You define tools and database connections in declaration 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 do declaration files work in Hyperterse?You define adapters (database connections) in app/adapters/ and tools in app/tools/. Each tool directory contains a declaration 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 declaration-driven: write SQL queries in declaration 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 declaration files. Hyperterse focuses on serving database queries as MCP tools with production-grade infrastructure, not on database abstraction or migrations.
Andrii Bidochko
CTO UBOS
Andrii Bidochko is an AI entrepreneur and researcher focused on AI agents, reinforcement learning, and autonomous systems. He writes about the technologies shaping the future of machine intelligence, from frontier models and agent architectures to real-world AI applications.