
MCP JSON-RPC Server
A beginner-friendly MCP-inspired JSON-RPC server built with Node.js, offering basic client-server interaction through an 'initialize' capabilities handshake and an 'echo' function.
README
MCP JSON-RPC Client and Server Example
This repository contains a simple, beginner-friendly example of an MCP-inspired JSON‑RPC client and server implemented in JavaScript. The project demonstrates a basic communication flow using Node.js's built‑in modules without any external dependencies.
Overview
-
Server (
server.js
):- Listens on TCP port 4000.
- Implements two JSON‑RPC methods:
initialize
: Returns a basic capabilities object (advertising an "echo" tool).echo
: Echoes back the parameters provided by the client.
-
Client (
client.js
):- Connects to the server on port 4000.
- Sends an
initialize
request followed by anecho
request. - Logs the responses received from the server.
Prerequisites
- Node.js installed on your system (v10 or later is recommended).
Getting Started
Installing via Smithery
To install MCP JSON-RPC Client and Server Example for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @melvincarvalho/mcpjs --client claude
Manual Installation
-
Clone the Repository:
git clone https://github.com/sandy-mount/mcpjs.git cd mcp-jsonrpc-example
-
Run the Server:
Open a terminal window and run:
node server.js
You should see a message like:
Server listening on port 4000
-
Run the Client:
Open another terminal window and run:
node client.js
The client will connect to the server, send the initialize and echo requests, and display the responses.
How It Works
-
The server listens for incoming TCP connections on port 4000. When it receives a JSON‑RPC message (each terminated by a newline), it processes the request:
- For the
initialize
method, it returns a JSON‑RPC response with basic capabilities and server info. - For the
echo
method, it returns the parameters that were sent in the request. - If an unknown method is requested, it responds with a JSON‑RPC error.
- For the
-
The client connects to the server, sends a JSON‑RPC
initialize
request, waits a short time, and then sends anecho
request. Responses from the server are printed to the console.
Files
- server.js — The JSON‑RPC server implementation.
- client.js — The JSON‑RPC client implementation.
Customization
You can extend this example by:
- Adding more JSON‑RPC methods to the server.
- Implementing additional error handling and logging.
- Experimenting with different transport protocols or adding TLS support.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Contributing
Feel free to open issues or submit pull requests with improvements or suggestions.
Happy coding!
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.

E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.