Node.js MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Node.js MCP Servercalculate (14.5 + 6.25) * 2 and round to 2 decimal places"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Node.js MCP Server
A small, stateless Model Context Protocol server built with Node.js, Express and the official MCP SDK. It is intended as a practical starting point: every tool has validated parameters, and the integration suite talks to a real local server through the MCP client transport.
Requirements
Node.js 18 or newer
npm
Related MCP server: mcp-tools-server
Run locally
npm install
npm startThe server listens on port 3000 by default. Override it with PORT=8080 npm start.
Endpoints:
GET /health- HTTP health checkPOST /mcp- stateless Streamable HTTP MCP endpoint
Example tools
Tool | What it demonstrates |
| Defaults, locale and IANA timezone parameters, structured output |
| Enum operations, optional decoration, bounded repeat count |
| Numeric parameters, rounding and an MCP tool error |
Every successful call returns text containing JSON, structuredContent, and isError: false. Expected tool failures still use HTTP 200 and return JSON such as {"error":"Division by zero is not allowed."} in the text content with isError: true.
Example arguments:
{
"operation": "divide",
"a": 10,
"b": 3,
"precision": 3
}Integration tests
npm testThe Mocha suite starts index.mjs as a child process on an available local port, waits until it is ready, connects with the official MCP client, exercises the health endpoint and tools, then shuts the process down in teardown. Chai is used for assertions.
MCP client URL
http://localhost:3000/mcpThe example is stateless: every MCP request gets a fresh server and transport.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA deployable MCP server for Cloudflare Workers or Azure Functions that provides example tools (time, echo, math), prompt templates for code assistance, and configuration resources. Enables AI assistants to interact with edge-deployed services through the Model Context Protocol.-
- AlicenseNot gradedqualityCmaintenanceA general-purpose MCP server with utility tools including datetime information, safe math calculations, text statistics, JSON extraction, knowledge base search, and HTTP GET requests. It demonstrates server-side MCP implementation and can be connected to Claude Desktop or LangGraph agents.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.1MIT
- FlicenseNot gradedqualityDmaintenanceEnables deployment of MCP servers over HTTP, providing ready-to-use tools for text processing, math calculations, and social media content generation, accessible to AI assistants like GitHub Copilot and Claude.-