What are the prerequisites?
Node.js 18+ and npm, the Bunnyshell CLI (`bns`) installed and configured, Claude Desktop, and optionally Docker and Docker Compose for Docker setup.
@aminalali8
基本信息
暂无概览
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A Model Context Protocol (MCP) server that enables AI assistants (like Claude) to interact with the Bunnyshell platform using its CLI (bns). It provides tools for managing Bunnyshell resources through natural language commands.
Clone the repository and run the setup script (./setup.sh or ./docker-setup.sh). Then start or restart Claude Desktop, connect to the MCP server by selecting 'bunnyshell-mcp' from the list, and provide your Bunnyshell API token. Alternatively, set the BNS_API_KEY environment variable in the Cursor configuration file.
DATABASE_URL) in an environmentNode.js 18+ and npm, the Bunnyshell CLI (`bns`) installed and configured, Claude Desktop, and optionally Docker and Docker Compose for Docker setup.
The token can be provided via command line, the `BNS_API_KEY` environment variable, or session storage (temporary, in-memory only). In Cursor, you can add it to the `env` section of `mcp.json`.
Yes. Use the `docker-setup.sh` script and configure the MCP server with Docker‑specific arguments in the Cursor configuration.
API tokens are never stored in code or configuration files. Commands are logged without sensitive information.
Yes. The `.cursor/mcp.json` file contains configuration for both local (`node dist/index.js`) and Docker setups, with the `BNS_API_KEY` environment variable for automatic authentication.
不止于 CSS
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
评论