drift MCP — Use Cases, Install & Live Demo

Why use it

Key features

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

What it looks like in practice

drift.replay ▶ ready

0/0

Install

Pick your client

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

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

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

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

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

claude mcp add drift -- uvx drift

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use 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

When to use: First session on a new repo, or after a big refactor that changed conventions.

Prerequisites

drift installed — uvx drift or install globally

Flow

Run the initial scan

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

→ 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'.✓ Copied

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

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

→ Claude recites the decisions you recorded

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

Pitfalls

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

Combine with: filesystem · github

Enforce team conventions during PR review

👤 Code reviewers ⏱ ~10 min intermediate

When to use: Before approving a PR, check it didn't silently break team patterns.

Flow

Load this PR's diff

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

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

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

→ Comment text per finding

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

Pitfalls

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

Combine with: github

Maintain a lightweight architecture decision log

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

When to use: Instead of a formal ADR folder no one updates.

Flow

Record a decision when made

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

→ Entry saved with ID
Query later when the question returns

Why did we pick Postgres?✓ Copied

→ The stored decision surfaces

Outcome: Institutional memory that survives turnover.

Combinations

Pair with other MCPs for X10 leverage

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.✓ Copied

drift + github

Review incoming PRs against recorded conventions

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

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
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

Cost & Limits

What this costs to run

API quota: None — fully local
Tokens per call: Convention summaries: ~1k tokens. Full scan dumps can be 10k+
Monetary: Free and open source
Tip: Load summary conventions at session start, not the full scan. Full scan only on refactor.

Security

Permissions, secrets, blast radius

Credential storage: Local SQLite or filesystem only

Data egress: 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.

Troubleshooting

Common errors and fixes

Scan hangs on a large monorepo

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

Verify: drift scan --dry-run

Memory query returns nothing relevant

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

Verify: 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.

Verify: claude mcp list

Alternatives

drift vs others

Alternative	When to use it instead	Tradeoff
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

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills