About MCP Server - JavaScript SDK
MCP Server - JavaScript SDK is an unofficial JavaScript SDK for developers building MCP servers. It organizes server content through separate definitions for prompts, resources, and tools.
Key features
- 01Define prompts
- 02Define resources
- 03Define tools and handlers
- 04Specify tool parameter schemas
- 05Create an MCP server instance
Use cases
- 01Build an MCP server in a JavaScript project
- 02Add prompts and resources to a server
- 03Implement and configure tool handlers
MCP support
The SDK is for building MCP servers and supports defining prompts, resources, and tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Server - JavaScript SDK
This is an unofficial JavaScript SDK for Model Context Protocol.
Usage
Import the package to your project:
npm install mcp-js-server
Create files to define the server's prompts, resources, and tools. See mcp-clever-demo, or the examples below:
Prompts
// prompts.js
export const prompts = {
hello_world: {
description: 'A simple prompt that says hello.',
arguments: [],
messages: [{
role: 'assistant',
content: {
type: 'text',
text: 'Hello, world!'
}
}]
}
};
Resources
// resources.js
export const resources = {
apiReference: {
uri: 'https://api.example.com/openapi.json',
mimeType: 'application/json'
}
};
Tools
// tools.js
export const tools = {
simple_tool: {
description: 'A simple tool',
handler: async () => new Date().toLocaleString(),
schema: {
type: 'object',
properties: {},
required: []
}
},
complex_tool: {
description: 'A complex tool',
handler: async ({ param1, param2 }) => {
return `param1: ${param1}, param2: ${param2}`;
},
schema: {
type: 'object',
properties: {
param1: { type: 'string' },
param2: { type: 'string' }
},
required: ['param1', 'param2']
}
}
};
Server
Then create a server instance with the following code:
// server.js
import { MCP } from 'mcp-server';
import { tools } from './tools.js';
import { prompts } from './prompts.js';
import { resources } from './resources.js';
const infos = {
name: 'mcp-demo-server',
version: '0.1.0'
};
const server = new MCP(infos, prompts, resources, tools);
Debugging
You can find logs of the server in your user system logs directory:
Linux: ~/.local/share/logs
macOS: ~/Library/Logs
Windows: %USERPROFILE%\AppData\Local\Logs
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.