mcp-stateless-starter

mcp-stateless-starter

Starter kit for building stateless MCP servers using the 2026 spec, enabling horizontal scaling without session affinity.

Category
Visit Server

README

Stateless MCP Server Starter (2026 Spec)

Production-ready Model Context Protocol server that scales horizontally on plain HTTP — no sticky sessions, no shared Redis, no deep packet inspection at the gateway. Aligned with the 2026-07-28 MCP Specification Release Candidate.

Why stateless

The 2025 MCP transport required sticky sessions and a shared session store to survive horizontal scale-out. The 2026 spec drops both. Any MCP request can land on any instance behind a round-robin load balancer.

This repo is the minimum example: an MCP server exposing two tools (echo, now) using the stateless HTTP transport, deployable to Vercel/Fly/Cloudflare Workers without changes.

Stack

  • Node 22 + TypeScript
  • @modelcontextprotocol/sdk (HTTP transport)
  • Zero state — every request is self-contained
  • Routes on Mcp-Method header so reverse proxies can shard without parsing JSON-RPC

Quick start

npm install
npm run dev          # http://localhost:3000/mcp
npm run test:client  # runs against local server

Deploy

# Vercel
vercel deploy

# Fly.io
fly launch

# Cloudflare Workers
wrangler deploy

All three work because the server holds zero session state between requests.

What changed vs 2025 transport

2025 (SSE + sessionId) 2026 (stateless HTTP)
Mcp-Session-Id header required No session header
Server holds session map Server holds nothing
Sticky LB required Round-robin LB works
tools/list re-requested per session Cached client-side per ttlMs
SSE stream for server→client Server-Sent Events optional, only for tasks primitive

File map

  • src/server.ts — Express server, single /mcp POST route
  • src/tools.ts — tool definitions (echo, now)
  • src/client.ts — example client that connects + calls a tool
  • vercel.json — zero-config Vercel deploy
  • Dockerfile — for Fly/Cloud Run

Resources

License

MIT — fork freely.


Built by Varritech. We turn AI prototypes into shipped products.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

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.

Official
Featured