This release adds 3 notable features for engineering teams evaluating rollout.
Published 2mo
MCP Developer Tools
✓ No known CVEs patched
✓ No known CVEs patched in this version
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
Summary
AI summaryFixed MCP serve command premature exit by adding keepalive interval and stdin handling.
Full changelog
Critical Fix
- MCP serve command no longer exits immediately — added keepalive interval and
process.stdin.resume()to prevent premature exit when launched by MCP clients (Claude Code, Codex, Gemini CLI) - Graceful cleanup on stdin end event
RLHF Loop Improvements
- Auto-regenerate prevention rules (Veto Layer) after negative feedback in
capture_feedback - Upgraded tool descriptions to encode mandatory session protocol
- Added Mandatory Session Protocol to CLAUDE.md
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
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.
Related context
Beta — feedback welcome: [email protected]