What dependencies are required?
Bun is used for package management, testing, and running scripts. Node.js is needed to run the compiled server.
@StevenStavrakis
Basic information
An opinionated starter template for making Model Context Protocol (MCP) servers
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-starter-template": {
"command": "bun",
"args": [
"run",
"scripts/create-tool.ts",
"<tool-name>"
]
}
}
}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 Starter is a production-ready template for building Model Context Protocol (MCP) servers with TypeScript. It provides a clean project structure, automated tool scaffolding, and developer tooling for fast testing and linting.
Clone the repository, install dependencies with bun install, and build with bun run build. Use bun run scripts/create-tool.ts <tool-name> to scaffold new MCP tools. Add the built server to Claude Desktop by editing the config file with the node command and path to dist/main.js.
Bun is used for package management, testing, and running scripts. Node.js is needed to run the compiled server.
Run `bun run scripts/create-tool.ts <tool-name>` – it creates a new tool directory with index, schema, and test files, and updates the tools index.
Build the project with `bun run build`, then add an entry to Claude Desktop’s configuration with command `node` and args pointing to `dist/main.js`.
Yes. Log in to npm, build the project, and run `npm publish`. Use `bun run release` to bump version numbers before publishing.
The README does not describe any built-in authentication or transport configuration; it is a starter template that you extend.

Agent-Native Terminal

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
Comments