claude-debugs-for-you MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

Language-agnostic — any VS Code-supported debugger works
Tools: set/remove breakpoints, continue, step, evaluate expressions, list stack
stdio or SSE transport from VS Code extension to MCP client
Works with Claude Desktop, Continue, Cursor
Requires a valid .vscode/launch.json

Живое демо

Как выглядит на практике

claude-debugs-for-you.replay ▶ готово

0/0

Установка

Выберите клиент

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

{
  "mcpServers": {
    "claude-debugs-for-you": {
      "command": "npx",
      "args": [
        "-y",
        "claude-debugs-for-you"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "claude-debugs-for-you": {
      "command": "npx",
      "args": [
        "-y",
        "claude-debugs-for-you"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "claude-debugs-for-you": {
      "command": "npx",
      "args": [
        "-y",
        "claude-debugs-for-you"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "claude-debugs-for-you": {
      "command": "npx",
      "args": [
        "-y",
        "claude-debugs-for-you"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "claude-debugs-for-you",
      "command": "npx",
      "args": [
        "-y",
        "claude-debugs-for-you"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "claude-debugs-for-you": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "claude-debugs-for-you"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add claude-debugs-for-you -- npx -y claude-debugs-for-you

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: claude-debugs-for-you

Let Claude drive the debugger to narrow down a bug

👤 Devs stuck on a non-obvious bug ⏱ ~20 min intermediate

Когда использовать: You've been reading logs for 20 minutes. Time to let Claude set strategic breakpoints and check variable state.

Предварительные требования

.vscode/launch.json with a runnable config — Use ${file} for the first config so Claude can run whichever file you have open
claude-debugs-for-you extension installed — VS Code Marketplace

Поток

Start the extension server

Start the debug MCP server. Note the path it prints and paste into Claude Desktop config.✓ Скопировано

→ Extension status bar shows running
Describe the bug

My function computeTotal() returns NaN when cart has sale items. Place a breakpoint at the start, step through, and tell me where it goes wrong.✓ Скопировано

→ Breakpoint set, program runs to it, Claude inspects locals
Diagnose

Based on the values at each step, what's the root cause and what's the smallest fix?✓ Скопировано

→ Root cause + patch

Итог: Bug found by Claude driving the debugger — faster than print-logging.

Подводные камни

launch.json is misconfigured and the debugger can't start — Test with F5 in VS Code first; only then let Claude drive
Claude sets too many breakpoints and slows everything to a crawl — Tell it to use conditional breakpoints where possible

Сочетать с: git-2

Understand a complex runtime state via expression evaluation

👤 Devs reverse-engineering unfamiliar code ⏱ ~15 min intermediate

Когда использовать: Code works but you don't know why. Set a breakpoint at a key line and ask Claude to explore the state.

Поток

Pause

Set a breakpoint at line X, run the test, and when paused tell me what's in scope.✓ Скопировано

→ Scope dump
Evaluate

Evaluate this.store.getState().users.filter(u => u.active).length. Then show me this.config.✓ Скопировано

→ Eval results

Итог: Live exploration without writing test code.

Подводные камни

Eval with side effects mutates state — Stick to read-only expressions unless you intend mutation

Комбинации

Сочетайте с другими MCP — эффект x10

claude-debugs-for-you + git-2

Debug → fix → commit loop

Debug the failing test, apply the fix you propose, then commit with a message describing what was wrong.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
set_breakpoint	file, line, condition?	Before/during a debug session	free
remove_breakpoint	id	Clean up between sessions	free
continue		Resume; returns next pause info	free
step_over		Single-step without entering functions	free
evaluate	expression: str	Inspect values at current pause point	free
get_stack		See call chain	free

Стоимость и лимиты

Во что обходится

Квота API: None
Токенов на вызов: Small per call; aggregate over a session can be 10-50k if you explore a lot of state
Деньги: Free, MIT
Совет: Ask Claude to form a hypothesis first, then verify with targeted breakpoints — avoids aimless stepping.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: None

Исходящий трафик: Local debugger; values shipped to your LLM provider

Никогда не давайте: Arbitrary `evaluate` on production databases via a debugger session

Evaluation can have side effects depending on the expression — treat with the care you'd give eval().
Don't run against production processes; use reproducible local environments.