Skip to content

This release includes 1 security fix for security teams reviewing exposed deployments.

Published 2mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →
This release patches 1 known CVE

Topics

agent-reliability ai-agents ai-cost-optimization ai-safety amp claude-code
+14 more
codex cursor developer-tools feedback-loop gemini guardrails mcp mcp-server opencode pre-action-checks reduce-llm-cost save-llm-tokens thompson-sampling thumbgate

Affected surfaces

auth

Summary

AI summary

Removed hardcoded bypass secrets from public code.

Full changelog

What's Changed

  • feat: add Cloudflare dynamic sandbox dispatch lane by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/548
  • security: remove hardcoded bypass secrets from public code by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/543
  • feat: prompt-level DLP — real-time PII scan, shadow detection, governance score by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/549
  • feat: in-app feedback widget + MCP tool for user issue reporting by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/546
  • feat: ephemeral agent store — per-agent isolation, auto-merge, compaction by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/551
  • feat: agent security hardening — cred attestation, privilege escalation, dependency gate by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/552

Full Changelog: https://github.com/IgorGanapolsky/ThumbGate/compare/v0.9.6...v0.9.7

Security Fixes

  • Removed hardcoded bypass secrets from public code — mitigates unauthorized access risk.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track IgorGanapolsky/mcp-memory-gateway

Get notified when new releases ship.

Sign up free

About IgorGanapolsky/mcp-memory-gateway

Pre-action gates that prevent AI coding agents from repeating known mistakes. Captures explicit feedback, auto-promotes failures into prevention rules, and enforces them via hooks.

All releases →

Beta — feedback welcome: [email protected]