What are the prerequisites?
Node.js 20 or later and npm (or pnpm) are required.
@SamMorrowDrums
Basic information
A minimal Model Context Protocol (MCP) server in TypeScript with hello tool, markdown resource, and prompt. Includes VS Code/devcontainer setup and documentation.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-typescript-starter": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"--",
"npx",
"tsx",
"src/stdio.ts"
]
}
}
}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.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
A feature-complete Model Context Protocol (MCP) server template written in TypeScript. It demonstrates all major MCP features (tools, resources, templates, prompts) with clean, production-ready code. Intended for developers who want to build or learn MCP servers.
Clone the repository, install dependencies with npm install, and build with npm run build. Run the server using npm run start:stdio for local development or npm run start:http for remote deployment. Development mode with live reload is available via npm run dev.
Node.js 20 or later and npm (or pnpm) are required.
Use `npm run dev` to start with `tsx watch` for instant reload on file changes.
It supports stdio transport (`npm run start:stdio`) for local development and HTTP transport (`npm run start:http`) running on port 3000 by default.
Use the MCP Inspector by running `npx @modelcontextprotocol/inspector -- npx tsx src/stdio.ts`. This provides a tools, resources, prompts, and logs tab for full debugging.
The project is licensed under the MIT License.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Public read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Give your AI agent the ability to see any webpage. Capture screenshots from Claude, Cursor, or any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, custom viewport, ad bloc
Comments