drift MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

drift.replay ▶ prêt

0/0

Installer

Choisissez votre client

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

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

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add drift -- uvx drift

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : 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

Quand l'utiliser : First session on a new repo, or after a big refactor that changed conventions.

Prérequis

drift installed — uvx drift or install globally

Déroulement

Run the initial scan

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

→ 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'.✓ Copié

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

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

→ Claude recites the decisions you recorded

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

Pièges

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

Combiner avec : filesystem · github

Enforce team conventions during PR review

👤 Code reviewers ⏱ ~10 min intermediate

Quand l'utiliser : Before approving a PR, check it didn't silently break team patterns.

Déroulement

Load this PR's diff

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

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

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

→ Comment text per finding

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

Pièges

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

Combiner avec : github

Maintain a lightweight architecture decision log

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

Quand l'utiliser : Instead of a formal ADR folder no one updates.

Déroulement

Record a decision when made

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

→ Entry saved with ID
Query later when the question returns

Why did we pick Postgres?✓ Copié

→ The stored decision surfaces

Résultat : Institutional memory that survives turnover.

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

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.✓ Copié

drift + github

Review incoming PRs against recorded conventions

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: None — fully local
Tokens par appel: Convention summaries: ~1k tokens. Full scan dumps can be 10k+
Monétaire: Free and open source
Astuce: Load summary conventions at session start, not the full scan. Full scan only on refactor.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : Local SQLite or filesystem only

Sortie de données : 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.

Dépannage

Erreurs courantes et correctifs

Scan hangs on a large monorepo

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

Vérifier : drift scan --dry-run

Memory query returns nothing relevant

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

Vérifier : 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.

Vérifier : claude mcp list

Alternatives

drift vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills