get_memory_versions
View edit history of a memory
How to use it
Project documentation lists get_memory_versions for the Cogmemai MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Cogmemai MCP
cogmemai-mcpOther tools in Cogmemai MCP (34)
Delete up to 100 memories at once
Update up to 50 memories at once (content, type, category, tags, etc.)
Merge related memories into comprehensive summaries using Ai
Permanently delete a memory
Delete a mandatory rule by ID
Export all memories as JSON for backup or transfer
Ai extracts facts from a conversation exchange automatically
Trigger Wisdom Engine to detect factual patterns across memory clusters
Signal whether a recalled memory was useful or irrelevant to improve future recall
Trigger skill generation from your corrections and preferences — or preview candidates with dry run
Memory health dashboard with self-tuning insights (filterable by project)
See what files changed since your last session
Explore the knowledge graph around a memory
Load top memories at session start (with smart ranking, health score, and session replay)
Find memories that may be outdated for review or cleanup
Retrieve tasks for the current project — pick up where you left off
Check your usage stats and tier info
Bulk import memories from a JSON array
Feed in a document (README, API docs) to auto-extract memories
Connect related memories with named relationships
Browse memories with filters (paginated, with untyped filter)
List all mandatory rules for the current project and/or globally
View all tags in use across your memories
Proactive recall. Fast recall to check prior context before making any suggestion
Promote a project memory to global scope
Search memories using natural language (semantic search)
Store a "wrong approach → right approach" pattern to avoid repeated mistakes
Store a fact explicitly (architecture decision, preference, etc.)
Save a mandatory rule that surfaces in every session — bypasses all scoring and decay
Save a summary of what was accomplished in this session
Create a persistent task with status and priority tracking
Set a reminder that surfaces at the start of your next session
Update content, importance, scope, type, category, subject, and tags
Change task status, priority, or description as you work