Skip to content
Back to search

hyperterse

The agentic server framework.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/hyperterse--hyperterse/badge.svg)](/listings/hyperterse--hyperterse)

HTML

<a href="/listings/hyperterse--hyperterse"><img src="/api/listings/hyperterse--hyperterse/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

Install

curl -fsSL https://hyperterse.com/install | bash

Initialize

hyperterse init

Generated starter structure:

.
├── .hyperterse
├── .agents/
│   └── skills/
│       ├── hyperterse-docs/
│       │   └── SKILL.md
│       └── hyperterse-agents/
│           └── SKILL.md
└── app/
    └── tools/
        └── hello-world/
            ├── config.terse
            └── handler.ts

Start

hyperterse start

With live reload:

hyperterse start --watch

Verify health

curl http://localhost:8080/heartbeat

Expected response:

{ "success": true }

Optional: list MCP tools

curl -s -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/list",
    "id": 1
  }' | jq

By design, Hyperterse exposes two transport-layer tools:

- `search` - discover project tools by natural language - `execute` - execute a project tool by name

Optional: discover project tools (search)

curl -s -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "search",
      "arguments": {
        "query": "hello world greeting"
      }
    },
    "id": 2
  }' | jq

Search hits include `name`, `description`, `relevance_score`, and `inputs`.

Execute a project tool

curl -s -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "execute",
      "arguments": {
        "tool": "hello-world",
        "inputs": { "name": "Hyperterse" }
      }
    },
    "id": 3
  }' | jq

Validate and build

hyperterse validate
hyperterse build -o dist
hyperterse serve dist/

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 334 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <!-- Start of - Dont change this block -->
  2. <div align="center">
  3. <picture>
  4. <img alt="Hyperterse — The agentic server framework." src="docs/assets/og.png" />
  5. </picture>
  6. </div>
  7. <br />
  8. <div align="center">
  9. <h1>Hyperterse</h1>
  10. </div>
  11. <p align="center">
  12. <strong>The agentic server framework.</strong><br />
  13. <a href="https://hyperterse.com">Website</a>
  14. •
  15. <a href="https://docs.hyperterse.com">Documentation</a>
  16. •
  17. <a href="#quick-start">Quick Start</a>
  18. •
  19. <a href="#tool-examples">Examples</a>
  20. •
  21. <a href="https://github.com/hyperterse/hyperterse">GitHub</a>
  22. </p>
  23. ---
  24. <!-- End of - Dont change this block -->
  25. **Hyperterse** is an **agentic server framework**: one build ships **agents** (A2A), **tools** (MCP), **prompts**, **resources**, database adapters, auth, caching, and observability from a single process. You declare surfaces in config; the compiler validates and bundles them. Clients use [MCP](https://modelcontextprotocol.io/) Streamable HTTP at `/mcp` for tools, prompts, and resources; [A2A](https://github.com/a2aproject/a2a-go)-style agent routes live at `/agent/{name}` when you define agents.
  26. ## Where to start
  27. - **Agents** — Declarative agents and A2A: [Agents overview](https://docs.hyperterse.com/agents/overview), [Agents quickstart](https://docs.hyperterse.com/agents/quickstart).
  28. - **Tools** — Callable MCP tools (DB or scripts): [Tools](https://docs.hyperterse.com/concepts/tools), [Scripts](https://docs.hyperterse.com/concepts/scripts), [Adapters](https://docs.hyperterse.com/concepts/adapters).
  29. - **Resources** — Static context for clients: [Resources](https://docs.hyperterse.com/concepts/resources).
  30. - **Prompts** — Reusable prompt templates: [Prompts](https://docs.hyperterse.com/concepts/prompts).
  31. The [Quickstart](https://docs.hyperterse.com/quickstart) walks through install, scaffold, and run, then optional MCP tool checks.
  32. ## What Hyperterse is for
  33. - Running **agents** alongside **MCP tools**, **prompts**, and **resources** in one deployable service
  34. - Exposing database queries and custom logic as MCP tools with declarative config
  35. - Production **Streamable HTTP** for MCP and **A2A** routes for agents
  36. - TypeScript handlers and transforms where config alone is not enough
  37. ## Core capabilities
  38. - **Agents**: declarative configs, tool-access policies, multi-provider models, per-agent A2A HTTP.
  39. - **Filesystem discovery**: one MCP tool per tool definition; prompts and resources follow the same discover-and-compile model (see [Project structure](https://docs.hyperterse.com/concepts/project-structure)).
  40. - **Execution models**: DB-backed tools (`use` + `statement`) or script-backed tools (`handler`).
  41. - **Database adapters**: PostgreSQL, MySQL, SQLite, MongoDB, Redis.
  42. - **Per-tool auth**: built-in `allow_all` and `api_key`, plus custom plugins.
  43. - **In-memory caching**: global defaults + per-tool overrides.
  44. - **Observability**: OpenTelemetry tracing/metrics + structured logging.
  45. ## Quick Start
  46. ### Install
  47. ```bash
  48. curl -fsSL https://hyperterse.com/install | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 61 on GitHub
  49. ```
  50. ### Initialize
  51. ```bash
  52. hyperterse init
  53. ```
  54. Generated starter structure:
  55. ```text
  56. .
  57. ├── .hyperterse
  58. ├── .agents/
  59. │ └── skills/
  60. │ ├── hyperterse-docs/
  61. │ │ └── SKILL.md
  62. │ └── hyperterse-agents/
  63. │ └── SKILL.md
  64. └── app/
  65. └── tools/
  66. └── hello-world/
  67. ├── config.terse
  68. └── handler.ts
  69. ```
  70. ### Start
  71. ```bash
  72. hyperterse start
  73. ```
  74. With live reload:
  75. ```bash
  76. hyperterse start --watch
  77. ```
  78. ### Verify health
  79. ```bash
  80. curl http://localhost:8080/heartbeat
  81. ```
  82. Expected response:
  83. ```json
  84. { "success": true }
  85. ```
  86. ### Optional: list MCP tools
  87. ```bash
  88. curl -s -X POST http://localhost:8080/mcp \
  89. -H "Content-Type: application/json" \
  90. -d '{
  91. "jsonrpc": "2.0",
  92. "method": "tools/list",
  93. "id": 1
  94. }' | jq
  95. ```
  96. By design, Hyperterse exposes two transport-layer tools:
  97. - `search` - discover project tools by natural language
  98. - `execute` - execute a project tool by name
  99. ### Optional: discover project tools (search)
  100. ```bash
  101. curl -s -X POST http://localhost:8080/mcp \
  102. -H "Content-Type: application/json" \
  103. -d '{
  104. "jsonrpc": "2.0",
  105. "method": "tools/call",
  106. "params": {
  107. "name": "search",
  108. "arguments": {
  109. "query": "hello world greeting"
  110. }
  111. },
  112. "id": 2
  113. }' | jq
  114. ```
  115. Search hits include `name`, `description`, `relevance_score`, and `inputs`.
  116. ### Execute a project tool
  117. ```bash
  118. curl -s -X POST http://localhost:8080/mcp \
  119. -H "Content-Type: application/json" \
  120. -d '{
  121. "jsonrpc": "2.0",
  122. "method": "tools/call",
  123. "params": {
  124. "name": "execute",
  125. "arguments": {
  126. "tool": "hello-world",
  127. "inputs": { "name": "Hyperterse" }
  128. }
  129. },
  130. "id": 3
  131. }' | jq
  132. ```
  133. ### Validate and build
  134. ```bash
  135. hyperterse validate
  136. hyperterse build -o dist
  137. hyperterse serve dist/
  138. ```
  139. ## Configuration model
  140. ### Project layout
  141. ```text
  142. my-project/
  143. ├── .hyperterse
  144. ├── app/
  145. │ ├── adapters/
  146. │ │ └── primary-db.terse
  147. │ └── tools/
  148. │ ├── get-user/
  149. │ │ ├── config.terse
  150. │ │ ├── input.ts
  151. │ │ └── output.ts
  152. │ └── get-weather/
  153. │ ├── config.terse
  154. │ └── handler.ts
  155. └── package.json
  156. ```
  157. ### Root config (`.hyperterse`)
  158. ```yaml
  159. name: my-service
  160. server:
  161. port: 8080
  162. log_level: 3
  163. tools:
  164. search:
  165. limit: 10
  166. cache:
  167. enabled: true
  168. ttl: 60
  169. ```
  170. ## Tool Examples
  171. ### DB-backed tool
  172. ```yaml
  173. description: "Get user by ID"
  174. use: primary-db
  175. statement: |
  176. SELECT id, name, email
  177. FROM users
  178. WHERE id = {{ inputs.user_id }}
  179. inputs:
  180. user_id:
  181. type: int
  182. auth:
  183. plugin: api_key
  184. policy:
  185. value: "{{ env.API_KEY }}"
  186. ```
  187. ### Script-backed tool
  188. ```yaml
  189. description: "Get weather by city"
  190. handler: "./handler.ts"
  191. inputs:
  192. city:
  193. type: string
  194. auth:
  195. plugin: allow_all
  196. ```
  197. Supported input types:
  198. - `string`
  199. - `int`
  200. - `float`
  201. - `boolean`
  202. - `datetime`
  203. Each tool must define exactly one execution mode:
  204. - `use` (adapter-backed), or
  205. - `handler` (script-backed)
  206. ## Runtime model
  207. **MCP** — Streamable HTTP at `/mcp` (JSON-RPC 2.0): tools, prompts, resources, completion, subscriptions. See [MCP transport](https://docs.hyperterse.com/runtime/mcp-transport).
  208. **A2A** — JSON-RPC per agent at `/agent/{agentName}` (agent card, messaging, tasks, streaming). See [A2A transport](https://docs.hyperterse.com/runtime/a2a-transport) and [Agents](https://docs.hyperterse.com/agents/overview).
  209. Execution pipeline:
  210. 1. Tool resolution
  211. 2. Authentication
  212. 3. Input transform (optional)
  213. 4. Execution (DB or handler)
  214. 5. Output transform (optional)
  215. 6. Response serialization
  216. ## MCP spec compliance
  217. Hyperterse implements the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) specification **[2025-11-25](https://modelcontextprotocol.io/specification/2025-11-25)**.
  218. Compliance status by component:
  219. | Spec component | Status |
  220. | ----------------------------------------------------------------------------------------------------------------------------- | :----: |
  221. | [Base protocol](https://modelcontextprotocol.io/specification/2025-11-25/basic) (JSON-RPC 2.0) | ✅ |
  222. | [Lifecycle](https://modelcontextprotocol.io/specification/2025-11-25/basic/lifecycle) (initialize/initialized) | ✅ |
  223. | [Tools](https://modelcontextprotocol.io/specification/2025-11-25/server/tools) (list, call, listChanged) | ✅ |
  224. | [Resources](https://modelcontextprotocol.io/specification/2025-11-25/server/resources) (list, read, subscribe, updated) | ✅ |
  225. | [Prompts](https://modelcontextprotocol.io/specification/2025-11-25/server/prompts) (list, get, listChanged) | ✅ |
  226. | [Completion](https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/completion) (ref/prompt, ref/resource) | ✅ |
  227. | [Pagination](https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/pagination) (cursor/nextCursor) | ⚠️ |
  228. | Tool result content types (image, audio, resource_link) | ⚠️ |
  229. Text content for tool results is supported; image, audio, and resource links are optional. Pagination applies when tools, prompts, or resources exceed typical small-to-medium counts.
  230. ## Security notes
  231. - Use `{{ env.VAR_NAME }}` for secrets and connection strings.
  232. - `{{ inputs.field }}` statement substitution is textual; enforce strict input schemas and safe query patterns.
  233. - Configure tool-level auth explicitly for production use.
  234. ## Documentation map
  235. - [Documentation index (`llms.txt`)](https://docs.hyperterse.com/llms.txt)
  236. - [Introduction](https://docs.hyperterse.com/introduction)
  237. - [Quickstart](https://docs.hyperterse.com/quickstart)
  238. - [Project structure](https://docs.hyperterse.com/concepts/project-structure)
  239. - **Agents** — [Overview](https://docs.hyperterse.com/agents/overview), [Agents quickstart](https://docs.hyperterse.com/agents/quickstart), [Tool access](https://docs.hyperterse.com/agents/tool-access), [Runtime API](https://docs.hyperterse.com/agents/runtime-api), [Model providers](https://docs.hyperterse.com/agents/model-providers)
  240. - **Tools** — [Tools](https://docs.hyperterse.com/concepts/tools), [Scripts](https://docs.hyperterse.com/concepts/scripts), [Adapters](https://docs.hyperterse.com/concepts/adapters)
  241. - **Resources** — [Resources](https://docs.hyperterse.com/concepts/resources)
  242. - **Prompts** — [Prompts](https://docs.hyperterse.com/concepts/prompts)
  243. - [Authentication](https://docs.hyperterse.com/concepts/authentication)
  244. - [MCP transport](https://docs.hyperterse.com/runtime/mcp-transport)
  245. - [A2A transport](https://docs.hyperterse.com/runtime/a2a-transport)
  246. - [Execution pipeline](https://docs.hyperterse.com/runtime/execution-pipeline)
  247. - [CLI reference](https://docs.hyperterse.com/reference/cli)
  248. - [Agent config](https://docs.hyperterse.com/reference/agent-config), [Prompt config](https://docs.hyperterse.com/reference/prompt-config), [Resource config](https://docs.hyperterse.com/reference/resource-config)
  249. - [Configuration schemas](https://docs.hyperterse.com/reference/configuration-schemas)
  250. ## Contributing
  251. 1. Fork the repo.
  252. 2. Create a feature branch.
  253. 3. Add or update tests.
  254. 4. Run validation locally.
  255. 5. Open a PR.
  256. See `CONTRIBUTING.md` and `CODE_OF_CONDUCT.md`.
  257. ---
  258. <p align="center">
  259. Agentic server framework—agents, tools, prompts, resources, one engine.<br />
  260. <a href="https://hyperterse.com">Website</a>
  261. •
  262. <a href="https://github.com/hyperterse/hyperterse">GitHub</a>
  263. •
  264. <a href="https://docs.hyperterse.com">Documentation</a>
  265. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.