MCP Server Docker Image for Choreo

by pcnfernando

180 downloads Not rated yet
GitHub

About

# MCP Server Docker Image for Choreo This Dockerfile creates a lightweight, secure, and production-ready Node.js-based server container that runs the Model Context Protocol (MCP) server using `supergateway`. The container is designed to be deployed as a service on Choreo. ## Running the Container Locally You can run…

Explore

- Node.js-based MCP server container using supergateway
- Lightweight, secure, and production-ready
- Configurable via environment variables (PORT, BASE_URL, etc.)
- Designed for deployment as a service on Choreo
- Exposes port 8000 for MCP communication
- Default server type: @modelcontextprotocol/server-github

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP Server Docker Image for Choreo
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

You can run the container using the following command:

docker run -p 8000:8000 \
  -e PORT=8000 \
  -e BASE_URL=http://localhost:8000 \
  -e SSE_PATH=/sse \
  -e MESSAGE_PATH=/message \
  -e DATA_FOLDER=/app/data \
  -e SERVER_TYPE=@modelcontextprotocol/server-github \
  mcp-server

The container supports the following environment variables:

| Variable | Default Value | Description |
|--------------|--------------------------|-------------|
| PORT | 8000 | The port on which the server listens. |
| BASE_URL | http://localhost:8000 | The base URL for the server. |
| SSE_PATH | /sse | Path for Server-Sent Events. |
| MESSAGE_PATH | /message | Path for messaging. |
| DATA_FOLDER | ./data | Directory for storing server data. |
| SERVER_TYPE | @modelcontextprotocol/server-github | Defines the type of MCP server to run. |

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp server docker image for choreo": {
            "mcp-server-hosting": {
                "command": "docker",
                "args": [
                    "run",
                    "-p",
                    "8000:8000",
                    "\\"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server-hosting": {
        "command": "docker",
        "args": [
            "run",
            "-p",
            "8000:8000",
            "\\"
        ]
    }
}

This Dockerfile creates a lightweight, secure, and production-ready Node.js-based server container that runs the Model Context Protocol (MCP) server using supergateway. The container is designed to be deployed as a service on Choreo.

Running the Container Locally

You can run the container using the following command:
docker run -p 8000:8000 \
  -e PORT=8000 \
  -e BASE_URL=http://localhost:8000 \
  -e SSE_PATH=/sse \
  -e MESSAGE_PATH=/message \
  -e DATA_FOLDER=/app/data \
  -e SERVER_TYPE=@modelcontextprotocol/server-github \
  mcp-server

Environment Variables

The container supports the following environment variables:

| Variable | Default Value | Description |
|--------------|--------------------------|-------------|
| PORT | 8000 | The port on which the server listens. |
| BASE_URL | http://localhost:8000 | The base URL for the server. |
| SSE_PATH | /sse | Path for Server-Sent Events. |
| MESSAGE_PATH | /message | Path for messaging. |
| DATA_FOLDER | ./data | Directory for storing server data. |
| SERVER_TYPE | @modelcontextprotocol/server-github | Defines the type of MCP server to run. |

Exposed Ports

- 8000: The main port where the MCP server runs.
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.