展示 HN：带有搜索和执行功能的 MCP 的声明式开源框架

展示 HN：带有搜索和执行功能的 MCP 的声明式开源框架
Show HN: Declarative open-source framework for MCPs with search and execute

## 超精简：摘要 Hyperterse 是一个免费且开源的框架（Apache 2.0 许可），用于构建 **MCP（模型上下文协议）** 工具服务器。它允许您轻松地将数据库访问暴露给 AI 助手和 LLM，而无需大量编码。您使用简单的 **声明文件** 定义工具和数据库连接（支持 PostgreSQL、MySQL、MongoDB、Redis）——指定 SQL 查询和输入类型。Hyperterse 然后编译、验证并将这些作为符合标准的、安全的 MCP 工具通过 JSON-RPC 2.0 提供。主要功能包括内置身份验证、缓存、可观察性和强大的数据库管理（连接池、健康检查）。虽然它不是 ORM——您编写原始 SQL——但 Hyperterse 会处理基础设施，确保数据安全，防止直接数据库访问，并提供可选的 TypeScript 处理程序以实现高级逻辑。本质上，Hyperterse 简化了使您的数据可供 AI 代理访问的过程。

## 超短文 2.0：AI 代理的安全数据访问 Samrith 发布了超短文 2.0，一个开源框架，旨在简化为 AI 代理构建机器理解提示 (MCP) 服务器。它解决了将代理安全连接到结构化数据的难题，无需脆弱的“胶水代码”或过于广泛的访问权限。超短文采用模式优先的方法，允许开发者为现有的数据库（Postgres、MySQL、MongoDB、Redis）定义受控接口。这会自动生成类型化的 MCP 工具，使代理能够仅通过简化的“搜索和执行”模式访问必要的数据——从而最大限度地减少 token 使用量。 2.0 版本专注于强大的 MCP 支持、改进的模式设计和增强的类型安全性。它非常适合构建 AI 代理、为 SaaS 平台添加 LLM 功能或需要安全内部数据访问的开发者。创建者欢迎反馈，特别是来自在生产环境中部署代理的用户的反馈。 [https://hyperterse.com](https://hyperterse.com) & [https://github.com/hyperterse/hyperterse](https://github.com/hyperterse/hyperterse)

原文

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 [email protected].

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.