updated mcp spec tut

updated mcp spec tut

An MCP server that demonstrates modern MCP spec features including elicitation (interactive confirm dialogs), signed request state, and cache hints, with a deploy tool requiring confirmation. It runs as both a Node server and a Cloudflare Worker, supporting stateless per-request handling.

Category
Visit Server

README

updated mcp spec tut

node typescript cloudflare workers

Small MCP server that plays with the newer bits of the spec: elicitation (interactive confirm dialogs), signed request state, and cache hints on tools/list. Ships as a plain Node server and as a Cloudflare Worker, same handler underneath.

What it does

The deploy tool needs confirmation before it does anything. If the connecting client supports elicitation, the server pops a real confirm dialog and mints a signed, short lived state token to track that flow. If the client doesn't support elicitation, it falls back to a confirm: true argument instead. legacy-client-test.ts exercises that fallback path directly.

Every request builds a fresh McpServer instance, so server_stats shows you the process is stateless per request while list_deployments proves you can still keep real state around (in memory here, for the demo).

Run it

npm install
npm run server   # starts on http://127.0.0.1:3000/mcp
npm run client   # connects, deploys, reads it back

Cloudflare Worker

Same MCP handler, just wired through worker.ts and wrangler.jsonc.

npx wrangler dev
npx wrangler deploy

Set STATE_KEY in production so every instance verifies request state with the same secret.

Files

  • bot.ts: the actual MCP server and tools
  • server.ts: Node entrypoint (Hono + @hono/node-server)
  • worker.ts: Cloudflare Worker entrypoint
  • client.ts: demo client with elicitation support
  • legacy-client-test.ts: demo client without it, uses the fallback

enjoy!! :)

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
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
Qdrant Server

Qdrant Server

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

Official
Featured