MCP Server Starter
A minimal, production-ready starter for building Model Context Protocol servers in TypeScript, supporting both stdio and streamable HTTP transports with optional bearer-token auth.
README
MCP Server Starter
A minimal, production-ready starter for building Model Context Protocol servers in TypeScript. One server definition runs two ways: over stdio for local clients, and over streamable HTTP when you deploy it, with optional bearer-token auth.
Features
- Two transports, one definition. Runs over stdio locally (Claude Code, Claude Desktop) and switches to streamable HTTP when
PORTis set. Tools live in one place. - Optional auth for HTTP. A shared bearer token, accepted via the
Authorizationheader or a?token=query param (some hosted clients can only pass a query param). - Typed tools. Inputs are validated with zod, so the model gets a clear schema and you get type safety.
- Deploy-ready. Stateless per request, with a
Dockerfileincluded. Runs on any container host. - Small and readable. A handful of files, no framework, easy to fork.
Quick start
git clone https://github.com/Axis-Data-Labs/mcp-server-starter
cd mcp-server-starter
npm install
cp .env.example .env
Run it locally over stdio:
npm run dev
Connect it to Claude Code
claude mcp add my-server -- npx tsx /absolute/path/to/mcp-server-starter/src/index.ts
Or add it to your client's MCP config:
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/mcp-server-starter/src/index.ts"]
}
}
}
Ask the model to call echo or add to confirm it works.
HTTP mode and deploying
Set PORT to run the streamable HTTP transport instead of stdio:
PORT=3000 MCP_AUTH_TOKEN=your-secret npm start
The server listens on POST /mcp. Point a remote MCP client at https://your-host/mcp and send the token as Authorization: Bearer your-secret (or ?token=your-secret). A Dockerfile is included, and most container platforms set PORT for you, so deploying is usually just pushing the repo.
Adding a tool
- Create
src/tools/<name>.tsand export aregister<Name>Tools(server)function. - Register tools with
server.tool(name, description, zodSchema, handler). - Call your
register…Tools(server)fromsrc/server.ts.
server.tool(
"greet",
"Greet someone by name.",
{ name: z.string().describe("Who to greet") },
async ({ name }) => ({ content: [{ type: "text", text: `Hello, ${name}` }] }),
);
Project structure
src/
index.ts picks the transport (stdio vs HTTP) at startup
server.ts builds the server and registers tools
http.ts streamable HTTP transport and optional auth
tools/
example.ts example tools, replace with your own
License
MIT. See LICENSE.
Built and maintained by Axis Data Labs.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.