mcpField
S
Simple MCP Server

Simple MCP Server

Local
github.com/kongo97Developer Tools0Updated 79w ago
Repository

About Simple MCP Server

Simple MCP Server is a lightweight server for exposing custom tools to AI clients over SSE. It includes weather examples and supports Docker Compose deployment with configurable host and port.

Key features

  1. 01Expose MCP tools over SSE
  2. 02Deploy with Docker Compose
  3. 03Configure host and port
  4. 04Includes weather tool examples

Use cases

  1. 01Connect an SSE-compatible MCP client
  2. 02Run example weather tools
  3. 03Deploy the server in a container

MCP support

The server exposes custom tools to MCP clients over SSE, with `/sse` endpoints for the event stream and JSON-RPC requests.

#mcp#server#ai-integration

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "simple-mcp-server-kongo97": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "compose"
      ]
    }
  }
}
Run commanddocker run -i --rm compose

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocicompose

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Simple MCP Server

A lightweight MCP (Model Context Protocol) Server implementation exposing custom tools via SSE for integration with AI clients.

Table of Contents

Overview

This repository provides a simple MCP Server that implements custom tools (e.g., weather lookups) and exposes them over Server-Sent Events (SSE). It can be run in a Docker container for quick deployment and integrates seamlessly with clients that support the MCP protocol.

Features

  • Exposes tools as MCP endpoints over SSE
  • Containerized for easy deployment via Docker Compose
  • Configurable port and host
  • Example tools included (e.g., weather alerts & forecast)

Prerequisites

  • Docker ≥ 20.10
  • Docker Compose ≥ 1.29

Getting Started

Clone the repository and navigate into the project directory:

git clone [email protected]:kongo97/simple-mcp-server.git
cd simple-mcp-server
Build the Docker Image
docker compose build

This will build the MCP Server image using the provided Dockerfile.

Start the Container
docker compose up -d

This command will:

  • Pull/build the image
  • Start the container in detached mode
  • Map port 8100 on the host to port 8100 in the container

To stop and remove the container, run:

docker compose down

Usage

Connecting an MCP Client

Configure your MCP-compatible client (e.g., Claude Desktop) to connect via SSE at:

http://localhost:8100/sse

Inside docs folder, you can find a simple configuration compatible with Claude Desktop (claude_desktop_config.json)

Available Endpoints
MethodPathDescription
GET/sseOpen SSE stream for MCP communication
POST/sseSend JSON-RPC requests over SSE

Configuration

You can customize the server port and host by setting environment variables in docker-compose.yml or directly in the container:

services:
  mcp-server:
    environment:
      - MCP_PORT=8100         # default port
      - MCP_HOST=0.0.0.0      # bind address

Development

  1. Edit or add your MCP tools in src/server.py (or your chosen file).
  2. Rebuild and restart the container: 
    docker compose build
docker compose up -d
  3. Check logs for errors: 
    docker compose logs -f

Troubleshooting

  • 404 on /sse: Ensure the server is bound to the correct port and path.
  • Connection refused: Verify Docker is running and the container is healthy: 
    docker ps
docker logs simple-mcp-server
  • Client errors: Check the client configuration for correct SSE URL and protocol version.

Comments

Markdown supported

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.