drift MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Pattern detection: auto-infers conventions from your actual code
Decision memory: write-once notes that persist across sessions
Multi-language: TypeScript, Rust, Java, Python, C#, PHP
MCP + offline CLI — same engine, two interfaces
Local-first: all data stored on your disk, nothing uploaded

Live-Demo

In der Praxis

drift.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

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

{
  "mcpServers": {
    "drift": {
      "command": "uvx",
      "args": [
        "drift"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "drift": {
      "command": "uvx",
      "args": [
        "drift"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "drift": {
      "command": "uvx",
      "args": [
        "drift"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "drift": {
      "command": "uvx",
      "args": [
        "drift"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "drift",
      "command": "uvx",
      "args": [
        "drift"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "drift": {
      "command": {
        "path": "uvx",
        "args": [
          "drift"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add drift -- uvx drift

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: drift

Onboard an AI assistant to your codebase's conventions

👤 Tech leads tired of reminding Claude 'no, we don't use classes here' ⏱ ~20 min beginner

Wann einsetzen: First session on a new repo, or after a big refactor that changed conventions.

Voraussetzungen

drift installed — uvx drift or install globally

Ablauf

Run the initial scan

Run drift scan on this repo. Tell me what patterns you detected around error handling, module structure, and naming.✓ Kopiert

→ Concrete convention summary with examples
Record decisions you want preserved

Record these team decisions: we use Result<T,E> not exceptions, one controller per feature folder, snake_case for file names. Tag them 'conventions'.✓ Kopiert

→ Confirmation; entries queryable later
Verify future sessions pick it up

In a new session: what conventions does this repo follow?✓ Kopiert

→ Claude recites the decisions you recorded

Ergebnis: Every future AI session starts with your team's conventions loaded — fewer corrections, more productive chats.

Fallstricke

Patterns are inferred from existing code, including bad code — Review the initial scan and delete any 'conventions' that are actually tech debt you're trying to escape
Decision memory drifts from reality if you forget to update it — Treat memory entries like docs — review quarterly

Kombinieren mit: filesystem · github

Enforce team conventions during PR review

👤 Code reviewers ⏱ ~10 min intermediate

Wann einsetzen: Before approving a PR, check it didn't silently break team patterns.

Ablauf

Load this PR's diff

Load the diff for PR #213 and compare it against the conventions drift has recorded.✓ Kopiert

→ List of convention-matches and misses
Draft review comments for deviations

For each deviation, draft a polite review comment citing the convention.✓ Kopiert

→ Comment text per finding

Ergebnis: Consistent PR reviews without the reviewer having to remember every unwritten rule.

Fallstricke

New patterns may be intentional — don't be dogmatic — Let the author override with a 'new pattern' decision that gets recorded for future PRs

Kombinieren mit: github

Maintain a lightweight architecture decision log

👤 Any team that keeps forgetting why choices were made ⏱ ~5 min beginner

Wann einsetzen: Instead of a formal ADR folder no one updates.

Ablauf

Record a decision when made

Record decision: we picked Postgres over DynamoDB because of ad-hoc query needs. Date today. Tags: db, architecture.✓ Kopiert

→ Entry saved with ID
Query later when the question returns

Why did we pick Postgres?✓ Kopiert

→ The stored decision surfaces

Ergebnis: Institutional memory that survives turnover.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

drift + filesystem

drift knows the conventions, filesystem does the edits

Using the conventions drift has recorded, refactor src/api/users.ts to match. Use filesystem to apply edits.✓ Kopiert

drift + github

Review incoming PRs against recorded conventions

Fetch PR #88, check it against drift conventions, draft review comments for any drift.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
scan_codebase	path: str	First session, or after large refactors	free; CPU-bound
list_conventions	tag?: str	Load context at session start	free
record_decision	title: str, body: str, tags?: str[]	When team agrees on something non-obvious	free
query_memory	query: str	When Claude should recall past context	free (local embeddings)
detect_pattern	area: str	Ad-hoc 'how do we normally do X here?'	free

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None — fully local
Tokens pro Aufruf: Convention summaries: ~1k tokens. Full scan dumps can be 10k+
Kosten in €: Free and open source
Tipp: Load summary conventions at session start, not the full scan. Full scan only on refactor.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Local SQLite or filesystem only

Datenabfluss: None by default — runs fully offline

Decision memory may contain sensitive business context. Add the drift data dir to .gitignore.
If you enable any cloud sync features, review what's leaving the machine.

Fehlerbehebung

Häufige Fehler und Lösungen

Scan hangs on a large monorepo

Exclude generated and vendor directories via .driftignore (same syntax as .gitignore).

Prüfen: drift scan --dry-run

Memory query returns nothing relevant

Rebuild local embeddings index; new decisions don't surface until indexed.

Prüfen: drift reindex

Claude doesn't use recorded conventions

Make sure the MCP is listed first in your client config so its context loads at the start of every session.

Prüfen: claude mcp list

Alternativen

drift vs. andere

Alternative	Wann stattdessen	Kompromiss
MARM-Systems	You want general cross-session memory not specific to code	Less code-aware; more general notes
llm-context.py	You want rule-driven code bundling rather than memory	No persistence layer
Plain ADRs in the repo	You prefer docs-as-code	AI has to read them each session — higher token cost

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen