How do I test or debug a sova server?
Use the CLI: `npx sova dev src/examples/addition.ts` to run a live test server, or `npx sova inspect src/examples/addition.ts` to open the MCP Inspector.
@The0wlGuy
基本情報
TypeScript framework for building MCP servers
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"sova": {
"command": "npx",
"args": [
"sova",
"dev",
"src/examples/addition.ts"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
sova is a TypeScript framework for building MCP (Model Context Protocol) servers that handle client sessions. It simplifies defining tools, resources, prompts and includes built‑in support for authentication, SSE, image/audio content, logging, and error handling. It is designed for developers who want to create MCP servers with minimal boilerplate.
Install via npm install sova. Create a server instance, add tools (or resources/prompts) using the addTool method with Standard Schema parameters, then start the server with server.start({ transportType: "stdio" }) or "sse". Use the CLI for testing (npx sova dev <file>) and debugging (npx sova inspect <file>).
imageContent, audioContent).dev) and debugging (inspect).Use the CLI: `npx sova dev src/examples/addition.ts` to run a live test server, or `npx sova inspect src/examples/addition.ts` to open the MCP Inspector.
sova runs on Node.js with npm. It uses the Standard Schema specification; any validation library (Zod, ArkType, Valibot) that implements it can be used. Valibot additionally requires `@valibot/to-json-schema` as a peer dependency.
Use the built‑in `imageContent` and `audioContent` helpers. They accept a URL, file path, or buffer, and return the correct MCP content object.
Throw a `UserError` instance inside a tool’s `execute` function. This error is shown to the user rather than causing an internal failure.
sova supports stdio for local communication and SSE (Server‑Sent Events) for remote MCP connections. SSE is configured via `server.start({ transportType: "sse", sse: { endpoint, port } })`.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Hindsight: Agent Memory That Learns

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Model Context Protocol Servers
コメント