buildwithclaude

This MCP server integrates the Build with Claude marketplace and plugin ecosystem with Claude Code. It exposes a curated collection of Agents, Commands, Hooks, Skills, and Plugins that you can browse, install, or invoke in your Claude Code workflows. Once running, you can use the marketplace tooling to search for plugins, install specific packages from the buildwithclaude collection, and leverage the provided agents and commands in your Claude-based automation. The server acts as a bridge that exposes the Build with Claude catalog to Claude Code clients, enabling discovery and seamless integration of community plugins into your projects.

Prerequisites:

• Node.js (LTS) installed on your machine
• Git installed
• Internet access to fetch dependencies

Step-by-step:

1. Clone the repository git clone https://github.com/davepoon/buildwithclaude.git cd buildwithclaude

2. Install dependencies npm install

3. Configure environment (optional but recommended)

   • Set CLAUDE_MARKETPLACE_URL to the desired marketplace endpoint if different from default
   • Ensure any required API keys or tokens are exported as environment variables if the server requires them

4. Run the MCP server node server.js

5. Verify the server is running by checking logs or hitting the MCP server health endpoint if available

Note: If you prefer a different runtime (e.g., uvx or Docker), adapt the commands accordingly using the provided mcp_config format.

Tips and common issues:

• Ensure Node.js is at a compatible version with the server codebase.
• If you encounter module resolution issues, run npm install from the repository root.
• If the marketplace URL or plugin catalog changes, update CLAUDE_MARKETPLACE_URL accordingly.
• For troubleshooting, check logs emitted by server.js and verify network connectivity to the marketplace endpoints.
• This MCP server references a curated set of agents, commands, hooks, skills, and plugins; to add your own, follow the repository's contribution guidelines and documentation embedded in the project.
• If you plan to deploy, consider containerizing the server (Docker) and mounting environment variables securely.