Categories › AI & Agents › Agent memory & context
Persistent memory layer that saves and recalls your project context and preferences.
Remote server: your requests and data go to mcp.memxus.com. Claude Code: claude mcp add --transport http memxus https://mcp.memxus.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
remember — Save important information to long-term memory. Always set collection when the topic is clear: project work → project:<slug>, personal tasterecall — Search long-term memory. Call list_collections when scope is unclear. For GitHub/Notion synced content use collection project:<slug> (unifieget_context — Builds a formatted context block for a topic from stored memories; use when the user asks to load or recall project context. Omit topic and list_memories — List recent memories in reverse-chronological order (read-only). When to use: audit what is saved, browse a collection, or collect memory IDget_memory — Retrieve the full content and metadata of one memory by its UUID. Use after list_memories or recall returned a truncated preview and you neelist_collections — List memory collections (folders/scopes) for this user. GitHub/Notion syncs appear under project:<slug> when unified collections are enabledforget — Permanently delete one memory by UUID. When to use: user asks to remove outdated or incorrect context, or to free plan storage. When NOT: fimemory_stats — Show aggregate statistics about stored memories: the total count, a breakdown by memory_type and by collection, and storage bytes used versuupdate — Update an existing memory by ID. Use mode replace (default) to patch fields, or append to extend content. Re-embeds only when content changeNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.