claude-mem MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Session-spanning memory via AI compression (not just grep of logs)
SQLite + Chroma vector search for semantic recall
Real-time web viewer at localhost:37777
<private> tags to exclude sensitive content from capture
Citation system — observations are referenced by ID in answers
Works with Claude Code, Gemini CLI, OpenCode; available via plugin marketplace

라이브 데모

실제 사용 모습

claude-mem-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "claude-mem-skill",
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "claude-mem-skill": {
      "command": {
        "path": "npx",
        "args": [
          "claude-mem",
          "install"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add claude-mem-skill -- npx claude-mem install

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: claude-mem

Resume a multi-week project without re-briefing Claude every morning

👤 Engineers on long-running features or research ⏱ ~5 min beginner

언제 쓸까: You spend the first 10 minutes of every session re-explaining context that Claude had yesterday.

사전 조건

Claude Code installed — npm install -g @anthropic-ai/claude-code
claude-mem installed — npx claude-mem install (registers hooks in ~/.claude)

흐름

Work normally

Just use Claude Code. claude-mem is passive — hooks capture events automatically.✓ 복사됨

→ localhost:37777 shows the memory stream updating as you work
Start tomorrow's session

Where did we leave off on the migration branch?✓ 복사됨

→ Claude recalls concrete facts + cites observation IDs
Correct misremembering

That's wrong about the DB schema — we decided to keep the v1 field. Mark that observation as corrected.✓ 복사됨

→ mem-search writes a correction; future recall prioritizes it

결과: Sessions feel continuous. The re-briefing ritual disappears.

함정

Memory recalls stale facts after you change course — Explicitly mark corrections; mem-search respects recency and overrides
Sensitive code snippets get captured — Wrap them in <private>...</private> tags; hooks skip private blocks

함께 쓰기: filesystem

Turn individual sessions into team knowledge without writing docs

👤 Team leads; ICs who avoid writing postmortems ⏱ ~10 min intermediate

언제 쓸까: You solve a gnarly bug, explain the fix to Claude, and want that explanation findable next month without writing a README.

흐름

Narrate your fix

Walk me through why the deadlock happened and the fix you just landed. Be complete — future me might read this.✓ 복사됨

→ Claude writes a narrative; compression captures it
Tag the memory

Tag this observation with 'db-deadlock-2026-04' and 'billing-cluster'.✓ 복사됨

→ Tags stored on the observation
Recall later

A month later: 'We've got another deadlock in billing — pull any prior notes.'✓ 복사됨

→ The April note surfaces first

결과: Lightweight knowledge base that grows by itself.

함정

Memory gets noisy as months pass — Use mem-search --prune on low-signal old sessions; Endless Mode (beta) handles this automatically

함께 쓰기: memory

Keep customer data and secrets out of memory captures

👤 Anyone working with sensitive data ⏱ ~15 min intermediate

언제 쓸까: You work on code that touches PII or secrets and can't let them land in a local vector store.

흐름

Wrap sensitive blocks

Write me the sample data with real test records wrapped in <private> tags so claude-mem doesn't capture the values.✓ 복사됨

→ Private blocks are in the transcript but not in the memory store
Verify

Open localhost:37777 and check today's stream. Confirm no records from the <private> block appear.✓ 복사됨

→ Private content absent
Add repo-wide policy

Update CLAUDE.md: 'Always wrap real customer data in <private>'.✓ 복사됨

→ CLAUDE.md updated; future sessions inherit

결과: Memory is useful without being a data-leak surface.

함정

Forgetting to tag sensitive content — Make it a pre-commit / hook convention; claude-mem can enforce prompts that remind on detection

조합

다른 MCP와 조합해 10배 효율

claude-mem-skill + filesystem

Memory recalls the file you edited, filesystem re-reads it

Pull from mem-search the last file we edited in the billing refactor; then read it and continue where we left off.✓ 복사됨

claude-mem-skill + serena

Memory supplies the intent; Serena supplies the current code state

Memory says we're renaming ChargeService → BillingService; use Serena to finish the rename.✓ 복사됨

claude-mem-skill + github

Cross-reference memory with real PR state

Memory says we opened a PR yesterday; use GitHub MCP to get its current status and review comments.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
mem-search (skill)	query: str, limit?: int, since?: date	Any time you'd ask Claude to 'remember' — full-text and semantic search over your history	free (local SQLite + embedding model)
mem-compress (hook)	session transcript	Automatic — runs at session end; rarely invoked manually	small Claude call per session
web viewer	URL http://localhost:37777	Debug what's being captured; check privacy filters	free

비용 및 제한

운영 비용

API 쿼터: Local SQLite + Chroma vectors; embedding model bundled
호출당 토큰: Small — observations are already compressed
금액: Free (MIT)
팁: Compression calls use your Claude API key; set a monthly budget in the claude-mem config if you chat a lot

보안

권한, 시크릿, 파급범위

자격 증명 저장: None for the tool itself; compression uses your existing Claude API key

데이터 외부 송신: Compression calls go to Anthropic (your account); nothing else leaves your machine

절대 부여 금지: Uploading the SQLite/Chroma store off-device without review — it contains transcripts

The local memory database is plaintext by default. If your disk isn't encrypted, enable FileVault/LUKS/BitLocker before using on sensitive projects.
Sharing your dotfiles or home dir via backup tools can leak memory. Add ~/.claude/mem/** to your backup exclusions if relevant.

문제 해결

자주 발생하는 오류와 해결

Web viewer at localhost:37777 won't load

Check the hook is running: ps aux | grep claude-mem. Reinstall with npx claude-mem install if it's absent.

확인: curl -I http://localhost:37777

Recall returns nothing useful

First few sessions are cold; memory gets better after ~10 sessions as patterns emerge. Also check that hooks are actually firing (see viewer).

확인: Open viewer during a session; events should stream in real time

Compression calls are expensive

Lower compression depth in config or use Endless Mode (beta) which is cheaper per session

확인: Check Anthropic usage dashboard for attribution

<private> content still shows up

Tag must be on its own lines; inline <private>…</private> in the middle of a sentence isn't parsed. Use block form.

확인: Reproduce and inspect the stored observation in the viewer

대안

claude-mem 다른 것과 비교

대안	언제 쓰나	단점/장점
Memory MCP	You want explicit, user-controlled memory writes — not passive capture	You do the memory-saving yourself; less ambient, less magic
Serena memory	Your use case is code-focused and you'd rather have per-project notes than transcript compression	No session-stream capture; more project-level
Just take notes	You prefer explicit, human-curated notes	No automation; discipline-dependent

claude-mem