Skip to main content
Testing an MCP App means assessing how well it integrates with the host, interacts with the model, and responds to the user. The tools below put these actors in the loop, each trading setup for fidelity.
ToUseReal modelReal hostInteractive
Iterate on tools and viewsDevTools
Verify behavior in ChatGPT and ClaudeTunnel
Check what the model does with your appPlayground
Validate before submissionAudit

DevTools

Call tools and render views locally, without a host

Tunnel

Expose your local server to real hosts

Playground

Chat with a real model running your app

Audit

Catch spec and platform issues before submission