v1.1.1

modelcontextprotocol/registryv1.1.1Jun 17, 2026by harijoe

AI Summary

This patch fixes the same caching issue as v0.36.4, ensuring that HTML files referenced in tool resources are served correctly regardless of the version query parameter.

Key Highlights

Resources now resolve by path instead of strictly requiring the version query param.
Version parameter is now treated as a cache-busting hint rather than a gate.

New Features

View resource serving fix for stale cache keys

Full Release Notes

## Patch release

### Explanation

ChatGPT used to cache the HTML file referenced in a tool resource indefinitely. This recently changed: the cache now lasts about 30min and is then refetched. Before this patch, Skybridge only served the HTML when the exact version hash was provided as a `?v=` query param, so resubmitting an app would break view rendering in all earlier conversations once their cache expired and they refetched the old hash.

### Fix
  
`resources/read` now resolves a view by its query-less path, so the underlying asset is served no matter what `?v=` value the consumer sends (stale cache key, mismatched version, or no param at all). The version param is only a cache-busting hint and no longer gates resolution. The consumer-facing URI is preserved on the response.
  
## Changes
- fix: serve view resource no matter the ?v= cache key @paulleseute (https://github.com/alpic-ai/skybridge/pull/872)