mcp-chaos-rig
A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry, all from a web UI.
How to use
The mcp-chaos-rig is a local Model Context Protocol (MCP) server designed to simulate various failure scenarios for your client applications. By breaking on demand, it allows developers to test their software against challenges such as authentication failures, tool disappearances, flaky responses, and token expiry—all through an intuitive web UI. This tool is essential for ensuring robust error handling and resilience in your applications.
Once you have connected to the mcp-chaos-rig server, you can easily trigger different failure scenarios from the web interface. You can simulate authentication failures by requesting invalid tokens, or test how your application handles tool disappearances by randomly removing tools during operation. Using the available commands, you can also initiate flaky responses to assess your client’s error management capabilities. For best results, try running a series of tests with varying configurations to thoroughly evaluate your application’s robustness.
How to install
Prerequisites
- Ensure you have Node.js installed on your machine (version 14.x or higher recommended).
Option A: Quick start with npx
You can quickly start the mcp-chaos-rig server using the following command:
npx -y mcp-chaos-rig
Option B: Global install alternative
Alternatively, you can install it globally on your system with:
npm install -g mcp-chaos-rig
After installation, you can start the server with:
mcp-chaos-rig
Additional notes
For optimal performance, consider adjusting the server's configuration settings as per your testing needs. You may want to set environment variables to customize error rates or response times. Common issues include ensuring that your client is correctly handling the various error scenarios that the server can simulate, so thorough testing is recommended.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
chrome-devtools
Chrome DevTools for coding agents
web-eval-agent
An MCP server that autonomously evaluates web applications.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.