cc-switch
A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode & Gemini CLI.
claude mcp add --transport stdio farion1231-cc-switch npx -y cc-switch
How to use
CC Switch is an all-in-one manager designed to streamline interactions with various AI coding models such as Claude Code, Codex, Gemini CLI, OpenCode, and OpenClaw. Users can easily switch between these models and manage their API interactions efficiently. The server provides a command-line interface that allows users to execute commands for each model, making it a versatile tool for developers working with AI coding services.
How to install
To install CC Switch, ensure you have Node.js installed on your machine. You can check if Node.js is installed by running node -v in your terminal. If it's not installed, download it from the official Node.js website. Once you have Node.js set up, you can install CC Switch by running the following command:
npx -y cc-switch
Additional notes
Make sure to check the environment variables required for each AI model you intend to use with CC Switch. Common issues may include API key misconfigurations or network connectivity problems. Refer to the documentation for each model for specific configuration options and troubleshooting tips.
Related MCP Servers
bridle
TUI / CLI config manager for agentic harnesses (Amp, Claude Code, Opencode, Goose, Copilot CLI, Crush, Droid)
mcp-image
MCP server for AI image generation and editing with automatic prompt optimization and quality presets (fast/balanced/quality). Powered by Gemini (Nano Banana 2 & Pro).
ask-user-questions
Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your LLMs ask questions to you. Be the human in the human-in-the-loop!
mcp-gearbox
A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents
PackageFlow
A visual DevOps hub for npm scripts, Git, workflows, and deploy — controllable by AI via MCP.
cadre-ai
Your AI agent squad for Claude Code. 17 specialized agents, persistent memory, desktop automation, and a common sense engine.
