physbox-mcp
Enables LLMs and MCP clients to interact programmatically with Flux, Volt, and Mesh simulation web applications via WebSocket relay.
README
PhysBox: MCP
PhysBox: MCP is a Model Context Protocol (MCP) server that enables LLMs and MCP clients (such as Claude Code or Claude Desktop) to interact programmatically with the three simulation web applications in the browser:
| Application | Production URL | Description |
|---|---|---|
| Flux | flux.physbox.io | Discrete-event / system-dynamics simulation (interactive React Flow graph) |
| Volt | volt.physbox.io | SPICE circuit simulation (powered by NgSpice WASM in browser) |
| Mesh | mesh.physbox.io | Rigid-body physics simulation (powered by MuJoCo WASM in browser) |
All communication is handled via JSON over WebSockets directly to the web app in your browser—no browser automation or DOM scraping is needed.
How It Works
PhysBox: MCP functions as a local companion server that establishes a WebSocket relay on port 3142.
When you open any of the simulation web apps, they connect directly to this WebSocket relay. When an MCP client executes a tool call, the command flows from the client to the companion server, gets forwarded to the active browser tab, and the results flow back.
MCP Client (e.g. Claude Desktop)
└── spawns → physbox-mcp (stdio)
└── WebSocket Server (ws://localhost:3142)
├── Flux
├── Volt
└── Mesh
Installation
Install the companion server directly from PyPI:
pip install physbox-mcp
Usage & Setup
1. Open the Web Applications
Launch or access the simulation web applications in your web browser:
- Flux: flux.physbox.io
- Volt: volt.physbox.io
- Mesh: mesh.physbox.io
As soon as a page finishes loading, it automatically registers with the companion WebSocket server.
2. Configure Your MCP Client
For Claude Desktop
Add the following block to your Claude Desktop configuration file (typically located at AppData/Roaming/Claude/claude_desktop_config.json on Windows or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"physbox-mcp": {
"command": "physbox-mcp",
"args": ["--stdio"]
}
}
}
For Claude Code
Add a .mcp.json file to your project root (or update your global configuration at ~/.claude/mcp.json):
{
"mcpServers": {
"physbox-mcp": {
"type": "stdio",
"command": "physbox-mcp",
"args": ["--stdio"]
}
}
}
3. Run the Companion Server Manually (Optional)
If you are running the server in HTTP mode rather than Stdio, you can run:
# Starts HTTP server listening on port 3141 (default)
physbox-mcp
Or configure custom port parameters:
physbox-mcp --port=4000
Development & Contribution
For instructions on local development, modifying schemas, extending tool definitions, and manual builds, please refer to [README_DEV.md](file:///wsl.localhost/Ubuntu-20.04/home/boab/expt_mcp/README_DEV.md).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.