Memory Quality Mcp

@xiaomeng

15 days ago

A Claude Code MCP plugin that audits and cleans up your AI memory. Claude Code v2.1.59+ automatically saves memories from your conversations. Over time, your memory store accumulates: Stale memories — "working on Project X this week" from months ago Junk memories — offhand remarks treated as permanent facts Conflicting memories — "prefers detailed comments" and "keep code clean and minimal" coexisting Misrecorded memories — AI over-interpreted a one-time comment as a fixed habit This plugin audits your memory store with a 4-dimension quality score (Importance / Recency / Credibility / Accuracy) and gives you actionable cleanup recommendations — with a visual dashboard.

Overview Tools Comments

Overview

Audit and clean up Claude Code's auto-saved memories.

Claude Code v2.1.59+ automatically saves memories from your conversations. Over time, your memory store accumulates stale project notes, junk memories, conflicting preferences, and over-interpreted one-off remarks.

Memory Quality MCP gives your memory store a health check:

• memory_audit() — instant scan, no LLM cost

• memory_report() — 4-dimension scoring (Importance / Recency / Credibility / Accuracy) with conflict detection

• memory_cleanup() — safe cleanup with dry-run preview + auto-backup to .trash/

• memory_dashboard() — visual health dashboard with scores and recommendations

Supports OpenAI, Anthropic, Kimi, MiniMax. Auto-detects language (EN/ZH) from system locale.

Try demo mode first — no real memory files needed: Open the memory dashboard in demo mode

Try in Playground

Server Config

{
  "mcpServers": {
    "memory-quality": {
      "command": "uvx",
      "args": [
        "memory-quality-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "your-key-here"
      }
    }
  }
}

Build with ShipAny.