Skip to main content
Glama

mcp-remote-server

by hemanth
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote
5

mcp-remote-server

A Model Context Protocol (MCP) server built with mcp-framework.

Quick Start

# Install dependencies npm install # Build the project npm run build # Start the server npm start

The server will run on port 1947 at endpoint /mcp by default.

Related MCP server: mcp-server-code-assist

Project Structure

mcp-remote-server/ ├── src/ │ ├── tools/ # MCP Tools │ │ └── XkcdTool.ts # Tool: Fetches random xkcd comics │ ├── resources/ # MCP Resources │ │ ├── DynamicResource.ts # Fetches data from JSONPlaceholder │ │ ├── RealTimeResource.ts # Echo WebSocket resource │ │ └── StaticResource.ts # Returns static JSON data │ └── index.ts # Server entry point ├── package.json ├── tsconfig.json └── README.md

Included Tools

XkcdTool

  • Name: xkcd

  • Description: Fetches a random xkcd comic image and its alt text.

Included Resources

DynamicResource

  • URI: resource://market-data

  • Description: Fetches data from JSONPlaceholder (free, no API key required).

EchoResource

  • URI: resource://echo

  • Description: Connects to a public WebSocket echo server (wss://echo.websocket.org).

StaticResource

  • URI: resource://static

  • Description: Returns static JSON data for testing.

Adding Components

You can add more tools using the CLI:

# Add a new tool mcp add tool my-tool

Tool Development Example

import { MCPTool } from "mcp-framework"; import { z } from "zod"; interface MyToolInput { message: string; } class MyTool extends MCPTool<MyToolInput> { name = "my_tool"; description = "Describes what your tool does"; schema = { message: { type: z.string(), description: "Description of this input parameter", }, }; async execute(input: MyToolInput) { // Your tool logic here return `Processed: ${input.message}`; } } export default MyTool;

Running and Testing

  1. Make changes to your tools or resources as needed.

  2. Run npm run build to compile.

  3. Start the server with npm start.

  4. The server will automatically load your tools and resources on startup.

Server Details

  • Port: 1947

  • Endpoint: /mcp

  • Transport: HTTP stream

  • Session management: Enabled

  • CORS: Enabled for all origins

Learn More

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

How are these scores calculated?

Resources

New MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hemanth/hello-remote-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server