Memory Quality Mcp

Created By
xiaomeng2 months 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

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

Server Config

{
  "mcpServers": {
    "memory-quality": {
      "command": "uvx",
      "args": [
        "memory-quality-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "your-key-here"
      }
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
xiaomeng
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago