MCP Server Demo
A minimal tool server demonstrating Model Context Protocol (MCP) interactions via local CLI and WebSocket transports. It provides tools for simple greeting responses and making external HTTP API calls using a configurable base URL.
README
MCP Server Demo
Quick demo to show the local MCP client/server example.
Prerequisites
- Node.js (16+)
Install (if you haven't already):
npm install
Run the demo (spawns multiple clients):
npm run demo
Or run a single client with a custom name:
node client.js Stephen
What it does
server.jsis a minimal newline-delimited JSON tool server exposingsay_hello.client.jsspawnsserver.js, sends{ tool: 'say_hello', args: { name } }, and logs the response.demo.jsruns severalclient.jsinstances concurrently to showcase multiple requests and responses.
Web demo
- Start the web demo server and open the UI in your browser:
npm run web
# then open http://localhost:3000 in a browser
The web UI lets you type a name and click "Send say_hello" to demonstrate the MCP request/response flow over WebSocket.
Calling external APIs from the server
- You can make the server call an external HTTP API via the
call_apitool.
Usage (CLI/stdin): send a request like:
{ "id": 1, "tool": "call_api", "args": { "path": "/status" } }
If EXTERNAL_API_BASE is set in the environment the path will be resolved relative to that base. Example (PowerShell):
$env:EXTERNAL_API_BASE = 'https://api.example.com'
echo '{ "id": 1, "tool": "call_api", "args": { "path": "/status" } }' | node server.js
The server will return a JSON response containing status, headers, and body (parsed JSON when possible).
Want a web-based demo or a demo that uses the installed @modelcontextprotocol/sdk transport? I can implement that next.
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
E2B
Using MCP to run code via e2b.