Bunnyshell MCP Server

A Model Context Protocol (MCP) server implementation for interfacing with the Bunnyshell platform through its CLI.

Overview

This project creates an MCP server that enables AI assistants (like Claude) to interact with the Bunnyshell platform using the Bunnyshell CLI (bns). The server provides a set of tools for managing your Bunnyshell resources through natural language commands.

Features

Organization Management: List and navigate organizations
Project Management: Create, list, and delete projects
Environment Management: Create, list, start, stop, and delete environments
Component Operations: Deploy, debug, and SSH into components
Variable & Secret Management: Manage environment variables and secrets
Remote Development: Start remote development sessions and set up port forwarding

Prerequisites

Node.js 18+ and npm
Bunnyshell CLI (bns) installed and configured
Claude Desktop
Docker and Docker Compose (for Docker setup)

Installation

Local Setup

Clone the repository:

git clone https://github.com/bunnyshell/bns-mcp.git
cd bns-mcp

Run the setup script:

./setup.sh

Docker Setup

Clone the repository:

git clone https://github.com/bunnyshell/bns-mcp.git
cd bns-mcp

Run the Docker setup script:

./docker-setup.sh

Usage

Start or restart Claude Desktop
Start a new conversation with Claude
Click '+' to add an attachment and select 'Connect to MCP server'
Choose 'bunnyshell-mcp' from the list of servers
Set your Bunnyshell API token:

token: YOUR_API_TOKEN

Example Commands

You can ask Claude to:

"List my organizations"
"Create a new project called 'MyProject' in organization ABC123"
"List all environments in project XYZ789"
"Start environment ENV123"
"Deploy component COMP456"
"Create a variable called 'DATABASE_URL' in environment ENV123"

Development

Project Structure

.
├── src/
│   ├── tools.ts       # Tool implementations
│   ├── utils.ts       # Utility functions
│   └── index.ts       # Server entry point
├── .cursor/
│   └── mcp.json      # Cursor MCP configuration
├── setup.sh          # Local setup script
├── docker-setup.sh   # Docker setup script
└── README.md         # Documentation

Cursor MCP Configuration

The .cursor/mcp.json file contains the configuration for the MCP server in Cursor:

{
  "mcpServers": {
    "bunnyshell-mcp": {
      "command": "node",
      "args": ["dist/index.js"],
      "env": {
        "BNS_API_KEY": "YOUR_API_TOKEN_HERE"
      }
    }
  }
}

For Docker setup, use:

{
  "mcpServers": {
    "bunnyshell-mcp": {
      "command": "docker",
      "args": ["exec", "-i", "bns-mcp-server", "node", "dist/index.js"],
      "env": {
        "BNS_API_KEY": "YOUR_API_TOKEN_HERE"
      }
    }
  }
}

Note: By adding your Bunnyshell API token to the env section, the MCP server will automatically use it for authentication without requiring you to provide it for each command. The code already checks for the BNS_API_KEY environment variable. This is especially useful for development and personal use. For shared environments, it's recommended to omit the token from configuration files and provide it during the conversation instead.

Building

npm install
npm run build

Running Tests

npm test

Security

API tokens are never stored in the code or configuration files
Tokens can be provided via:
- Command line options
- Environment variable (BNS_API_KEY)
- Session storage (temporary, in-memory only)
Command logging omits sensitive information

Contributing

Fork the repository
Create a feature branch
Commit your changes
Push to the branch
Create a Pull Request

License

MIT License

Bunnyshell Platform