What are the runtime requirements for MCP Server Template?
Bun v1.0.0 or higher is required; Node.js v18.0.0+ is needed for some dependencies. Supported operating systems are macOS 12+, Linux with glibc 2.31+, and Windows 10+ (via WSL).
@tkc
Basic information
MCP starter kit for building AI tools with Bun runtime - specialized for interactive quizzes
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-template-tkc": {
"command": "bun",
"args": [
"start"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
MCP Server Template is a starter kit for building AI tools with the Bun runtime, specifically providing a specialized quiz-focused Model Context Protocol (MCP) server implementation. It is intended for developers who want to create interactive quiz tools integrated with AI assistants via the MCP protocol.
Clone the repository, install dependencies with bun install, then run the server using bun start (production) or bun dev (development with auto-restart). For Claude Desktop integration, add a JSON entry specifying the Bun command and path to the server entry point (src/index.ts).
Bun v1.0.0 or higher is required; Node.js v18.0.0+ is needed for some dependencies. Supported operating systems are macOS 12+, Linux with glibc 2.31+, and Windows 10+ (via WSL).
Modify the `quizQuestions` object in `src/index.ts` by adding a new key with arrays for each difficulty level, then update the `QuizSchema` enum to include the new category name.
The project includes Jest integration tests located in `tests/cli-mcp.test.ts`. Run all tests with `bun test`.
The server provides one tool called `get_quiz`, which accepts a `category` and `difficulty` argument and returns quiz questions from the specified category and difficulty level.
Add an entry to your Claude Desktop configuration JSON with `command` set to the Bun binary path and `args` containing `["run", "<full path to src/index.ts>"]`. The server is then available as an MCP tool.
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
Comments