Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.hyperterse.com/llms.txt

Use this file to discover all available pages before exploring further.

Any serious AI workload needs the same backbone: safe access to data, clear inputs, authentication, caching, observability, and protocols that models and agent runtimes actually speak. Hyperterse is an agentic server framework. You describe agents, tools, prompts, and resources in declarative config. The engine validates and compiles them, then serves MCP for tool, prompt, and resource surfaces, and agent HTTP when you define agents. You keep ownership of data and business rules; the framework handles plumbing and protocol edges.

​
What you can build

You can expose databases and custom logic as tools, ship reusable prompt templates and resources, and run A2A-compatible agents on shared adapters and policies. A typical database-backed tool looks like this: 
description: 'Get user by ID'
use: primary-db
statement: 'SELECT id, name, email FROM users WHERE id = {{ inputs.user_id }}'
inputs:
  user_id:
    type: int
    required: true
auth:
  plugin: api_key
  policy:
    value: '{{ env.API_KEY }}'
That yields an MCP tool named get-user that runs your query, validates inputs, and enforces API keys—without hand-rolling a service layer for each action.

​
How it works

1

Describe what you need

Add adapters, tools, and optionally prompts, resources, and agents. Each surface is declared in config; Hyperterse validates and links them.
2

Compile your project

Run hyperterse build to validate configuration, bundle scripts, and emit a deployable artifact.
3

Serve

Run hyperterse serve (or hyperterse start in development) so MCP and agent routes go live from that artifact.
During development, hyperterse start --watch rebuilds when files change so you can skip manual compile cycles.
Hyperterse lifecycle: build steps then a live server

​
Key capabilities

Agents (A2A)

Declarative agents with model providers, tool access rules, and dedicated HTTP endpoints for agent-style workflows.

Tools (MCP)

One declarative definition per tool—database-backed or script-backed—with discovery and validation at compile time.

Prompts

Reusable prompt templates with arguments, completions, and multi-message scaffolding for MCP clients.

Resources

Static or templated read-only context for resources/list and resources/read, with optional subscriptions when content changes.

Database adapters

Connect to PostgreSQL, MySQL, SQLite, MongoDB, or Redis. Pooling, health checks, and shutdown are handled for you.

Embedded scripting

TypeScript handlers and transforms when pure config is not enough. Scripts run in a sandbox with fetch and console.

Per-tool authentication

Attach auth per tool with built-in plugins or your own—no global middleware required.

In-memory caching

Cache tool results globally or per tool with a TTL so repeat calls stay cheap.

Observability

OpenTelemetry tracing, metrics, and structured logging for operations and debugging.

​
Next steps

Install the CLI

Set up Hyperterse on your machine in under a minute.

Quickstart

Install, scaffold, run, and optional MCP checks against the sample tool.