“When two ruflo MCP servers share one memory store, memory_retrieve on one server keeps returning a value after the other server has updated or deleted it.”
Quote · github.com
From “memory_retrieve serves stale or deleted values when two MCP servers share a store (per-process cache)”, found 2026-10-14.
Shown with a two-process reproducer: a per-process cache served old values for up to five minutes while the database held the right one. Fixed by PR #3361 in September 2026.