Claude Code MCP Enhanced
🤖 Клод Код MCP Сервер
Хотите быстро начать? Ознакомьтесь с нашим руководством QUICKSTART.md !
Этот проект представляет собой ответвление steipete/claude-code-mcp с расширенными возможностями оркестровки, улучшениями надежности и дополнительной документацией.
Расширенный сервер Model Context Protocol (MCP), позволяющий запускать Claude Code в режиме одноразового запуска с автоматическим обходом разрешений. Этот сервер включает расширенные возможности оркестровки задач, надежную обработку ошибок и «шаблон бумеранга» для разбиения сложных задач на управляемые подзадачи.
Вы заметили, что стандартные помощники ИИ иногда испытывают трудности со сложными, многошаговыми правками или операциями? Этот сервер с его мощным унифицированным инструментом claude_code и улучшенными функциями надежности призван сделать Claude более прямым и способным агентом для ваших задач кодирования.
🔍 Обзор
Этот сервер MCP предоставляет мощные инструменты, которые могут использоваться LLM для взаимодействия с Claude Code. При интеграции с Claude Desktop или другими клиентами MCP он позволяет LLM:
Запустить Claude Code с обходом всех разрешений (используя
--dangerously-skip-permissions)Выполнять код Клода с любой подсказкой без прерываний на разрешение
Прямой доступ к возможностям редактирования файлов
Выполнение сложных многошаговых операций с надежной обработкой ошибок и повторными попытками
Организуйте задачи с помощью специализированных ролей агентов, используя модель «бумеранга»
Поддерживайте надежное выполнение с помощью механизмов пульсации для предотвращения тайм-аутов
Related MCP server: Scenario Word
✨ Преимущества
Повышенная надежность: надежная обработка ошибок, автоматические повторные попытки, плавное завершение работы и отслеживание запросов.
Оркестровка задач: сложные рабочие процессы можно разбить на специализированные подзадачи.
Автоматизация задач: автоматическое преобразование понятных человеку списков задач Markdown в исполняемые команды MCP.
Оптимизация производительности: улучшенное выполнение с кэшированием конфигурации и эффективностью использования ресурсов
Лучший мониторинг: API проверки работоспособности, подробные отчеты об ошибках и комплексное ведение журнала
Опыт разработчика: горячая перезагрузка конфигурации, гибкое управление средой и упрощенный API
Плюс все стандартные преимущества Claude Code:
У Claude/Windsurf часто возникают проблемы с редактированием файлов. У Claude Code это получается лучше и быстрее.
Несколько команд могут быть поставлены в очередь вместо прямого выполнения. Это экономит контекстное пространство, поэтому более важная информация сохраняется дольше.
Файловые операции, git или другие операции не требуют дорогостоящих моделей. Claude Code экономически эффективен, если вы зарегистрируетесь в Anthropic Max.
У Клода более широкий доступ к системе, поэтому, когда стандартные помощники застревают, просто попросите их «использовать код Клода», чтобы разблокировать прогресс.
📝 Предварительные условия
Node.js v20 или более поздней версии (используйте fnm или nvm для установки)
Claude CLI установлен локально (запустите его и вызовите /doctor) и
-dangerously-skip-permissionsпринят.
💾 Установка и использование
Вы можете установить и использовать этот MCP-сервер тремя различными способами:
🚀 Метод 1: через URL-адрес GitHub (рекомендуется)
Самый гибкий метод — установка напрямую из GitHub с помощью npx . Это всегда извлекает последнюю версию из репозитория.
Добавьте в файл .mcp.json следующее:
{
"mcpServers": {
"claude-code-mcp-enhanced": {
"command": "npx",
"args": [
"github:grahama1970/claude-code-mcp-enhanced"
],
"env": {
"MCP_CLAUDE_DEBUG": "false",
"MCP_HEARTBEAT_INTERVAL_MS": "15000",
"MCP_EXECUTION_TIMEOUT_MS": "1800000"
}
}
}
}📦 Метод 2: Через пакет npm
Если пакет опубликован в npm, вы можете установить его, используя имя пакета npm:
{
"mcpServers": {
"claude-code-mcp-enhanced": {
"command": "npx",
"args": [
"-y",
"@grahama1970/claude-code-mcp-enhanced@latest"
],
"env": {
"MCP_CLAUDE_DEBUG": "false",
"MCP_HEARTBEAT_INTERVAL_MS": "15000",
"MCP_EXECUTION_TIMEOUT_MS": "1800000"
}
}
}
}🔧 Метод 3: Локальная установка
В целях разработки или тестирования вы можете запустить сервер из локальной установки:
Клонируйте репозиторий:
git clone https://github.com/grahama1970/claude-code-mcp-enhanced.git cd claude-code-mcp-enhancedУстановка зависимостей и сборка:
npm install npm run buildНастройте файл
.mcp.jsonдля использования локального сервера:
{
"mcpServers": {
"claude-code-mcp-enhanced": {
"command": "node",
"args": [
"/path/to/claude-code-mcp-enhanced/dist/server.js"
],
"env": {
"MCP_CLAUDE_DEBUG": "false",
"MCP_HEARTBEAT_INTERVAL_MS": "15000",
"MCP_EXECUTION_TIMEOUT_MS": "1800000"
}
}
}
}🔑 Важная первоначальная настройка: принятие разрешений
Прежде чем сервер MCP сможет успешно использовать инструмент claude_code , необходимо сначала вручную запустить CLI Claude один раз с флагом --dangerously-skip-permissions , войти в систему и принять условия.
Это единовременное требование Claude CLI.
npm install -g @anthropic-ai/claude-codeclaude --dangerously-skip-permissionsСледуйте подсказкам, чтобы принять. После этого сервер MCP сможет использовать флаг неинтерактивно.
При первом запуске инструмента macOS может запросить различные разрешения для папок, и первый запуск может завершиться неудачей. Последующие запуски будут работать нормально.
🔗 Подключение к вашему MCP-клиенту
После настройки сервера вам необходимо настроить ваш клиент MCP (например, Cursor, Claude Desktop или другие, использующие mcp.json или mcp_config.json ).
Пример файла конфигурации MCP
Вот пример того, как добавить сервер Claude Code MCP в ваш файл .mcp.json :
{
"mcpServers": {
"Local MCP Server": {
"type": "stdio",
"command": "node",
"args": [
"dist/server.js"
],
"env": {
"MCP_USE_ROOMODES": "true",
"MCP_WATCH_ROOMODES": "true",
"MCP_CLAUDE_DEBUG": "false"
}
},
"other-services": {
// Your other MCP services here
}
}
}Места конфигурации MCP
Конфигурация обычно выполняется в файле JSON. Имя и местоположение могут различаться в зависимости от вашего клиента.
Курсор
Курсор использует mcp.json .
macOS:
~/.cursor/mcp.jsonWindows:
%APPDATA%\\Cursor\\mcp.jsonLinux:
~/.config/cursor/mcp.json
Виндсерфинг
Пользователи Windsurf используют mcp_config.json
macOS:
~/.codeium/windsurf/mcp_config.jsonWindows:
%APPDATA%\\Codeium\\windsurf\\mcp_config.jsonLinux:
~/.config/.codeium/windsurf/mcp_config.json
(Примечание: в некоторых смешанных установках, если также установлен Cursor, эти клиенты могут вернуться к использованию пути Cursor ~/.cursor/mcp.json . Отдайте приоритет специфичным для Codeium путям, если используете расширение Codeium.)
Создайте этот файл, если его нет.
🛠️ Предоставляемые инструменты
Этот сервер предоставляет три основных инструмента:
claude_code 💬
Выполняет запрос напрямую с помощью Claude Code CLI с --dangerously-skip-permissions .
Аргументы:
prompt(строка, обязательно): Подсказка для отправки Клоду Коду.workFolder(строка, необязательно): рабочий каталог для выполнения Claude CLI, необходимый при использовании файловых операций или при обращении к любому файлу.parentTaskId(строка, необязательно): идентификатор родительской задачи, создавшей данную задачу (для оркестровки задач/бумеранга).returnMode(string, необязательно): Как должны возвращаться результаты: «summary» (краткий) или «full» (подробный). По умолчанию «full».taskDescription(строка, необязательно): Краткое описание задачи для лучшей организации и отслеживания в организованных рабочих процессах.mode(строка, необязательно): если MCP_USE_ROOMODES=true, указывает режим Roo для использования (например, «boomerang-mode», «coder», «designer» и т. д.).
health 🩺
Возвращает состояние работоспособности, информацию о версии и текущую конфигурацию сервера Claude Code MCP.
Пример запроса на проверку работоспособности:
{
"toolName": "claude_code:health",
"arguments": {}
}Пример ответа:
{
"status": "ok",
"version": "1.12.0",
"claudeCli": {
"path": "claude",
"status": "available"
},
"config": {
"debugMode": true,
"heartbeatIntervalMs": 15000,
"executionTimeoutMs": 1800000,
"useRooModes": true,
"maxRetries": 3,
"retryDelayMs": 1000
},
"system": {
"platform": "linux",
"release": "6.8.0-57-generic",
"arch": "x64",
"cpus": 16,
"memory": {
"total": "32097MB",
"free": "12501MB"
},
"uptime": "240 minutes"
},
"timestamp": "2025-05-15T18:30:00.000Z"
}convert_task_markdown 📋
Конвертирует файлы задач markdown в формат JSON, совместимый с Claude Code MCP.
Аргументы:
markdownPath(строка, обязательно): путь к файлу задачи разметки для преобразования.outputPath(строка, необязательно): Путь, куда сохранить вывод JSON. Если не указано, возвращает JSON напрямую.
Пример запроса:
{
"toolName": "claude_code:convert_task_markdown",
"arguments": {
"markdownPath": "/home/user/tasks/validation.md",
"outputPath": "/home/user/tasks/validation.json"
}
}Примеры сценариев использования
1. Базовая операция кода
Пример запроса MCP:
{
"toolName": "claude_code:claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nRefactor the function foo in main.py to be async.",
"workFolder": "/path/to/project"
}
}2. Оркестровка задач (шаблон «Бумеранг»)
Запрос родительской задачи:
{
"toolName": "claude_code:claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nOrchestrate the implementation of a new API endpoint with the following subtasks:\n1. Create database models\n2. Implement API route handlers\n3. Write unit tests\n4. Document the API",
"workFolder": "/path/to/project"
}
}Запрос подзадачи (создан родителем):
{
"toolName": "claude_code:claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nCreate database models for the new API endpoint as specified in the requirements.",
"workFolder": "/path/to/project",
"parentTaskId": "task-123",
"returnMode": "summary",
"taskDescription": "Database model creation for API endpoint"
}
}3. Запрос специализированного режима
Пример использования режима Roo:
{
"toolName": "claude_code:claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nCreate unit tests for the user authentication module.",
"workFolder": "/path/to/project",
"mode": "coder"
}
}🔄 Конвертер задач
Сервер MCP включает мощный инструмент-конвертер задач, который автоматически преобразует понятные человеку списки задач Markdown в полностью исполняемые команды MCP. Этот интеллектуальный конвертер устраняет разрыв между тем, как люди думают о задачах, и тем, как машины их выполняют.
Полный рабочий процесс
graph TD
A["👤 User"] -->|"Create tasks.md"| B["📝 Multi-Task Markdown"]
A -->|"Prompt Claude"| C["🤖 Claude Desktop"]
C -->|"Use convert_task_markdown"| D["🔄 Task Converter MCP"]
D -->|"Validate Format"| E{"Format Valid?"}
E -->|"No"| F["📑 Error + Fix Instructions"]
F -->|"Return to User"| A
E -->|"Yes"| G["📋 MCP Task List"]
G -->|"Execute Task"| H1["⚡ Claude Task #1"]
H1 -->|"Complete"| I1["Next Task"]
I1 -->|"Execute Task"| H2["⚡ Claude Task #2"]
H2 -->|"Complete"| I2["Next Task"]
I2 -->|"Execute Task"| H3["⚡ Claude Task #3"]
H3 -->|"Complete"| I3["More Tasks"]
I3 -->|"Execute Task"| HN["⚡ Claude Task #N"]
HN -->|"Complete"| IN["🎉 All Tasks Completed!"]
style A fill:#4A90E2,stroke:#fff,stroke-width:2px,color:#fff
style C fill:#7C4DFF,stroke:#fff,stroke-width:2px,color:#fff
style D fill:#00BCD4,stroke:#fff,stroke-width:2px,color:#fff
style F fill:#FF5252,stroke:#fff,stroke-width:2px,color:#fff
style G fill:#4CAF50,stroke:#fff,stroke-width:2px,color:#fff
style H1 fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
style H2 fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
style H3 fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
style HN fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
style IN fill:#4CAF50,stroke:#fff,stroke-width:2px,color:#fffЭтапы рабочего процесса
Пользователь добавляет MCP в свой файл конфигурации
Пользователь подсказывает Клоду : «Используйте convert_task_markdown для выполнения моего файла tasks.md»
MCP автоматически :
Загружает файл разметки
Проверяет формат (возвращает ошибки, если разделы отсутствуют)
Преобразует понятные человеку задачи в точные исполняемые команды
Возвращает JSON, который Клод Код может выполнить последовательно
Клод получает JSON и может выполнить каждую задачу с помощью инструмента
claude_code
Основные характеристики
Автоматическое разрешение путей: преобразует общие инструкции, такие как «изменить каталог для проекта», в точные исполняемые команды с полными путями.
Интеллектуальный перевод команд: преобразует инструкции на английском языке в точные команды терминала (например, «активировать виртуальную среду» →
source .venv/bin/activate)Соответствие протоколу MCP: гарантирует, что все выходные данные на 100% совместимы с протоколом контекста модели.
Никакой двусмысленности: все сгенерированные команды используют точные пути и исполняемый синтаксис — никаких заполнителей или общих ссылок.
Проверка формата: обеспечивает правильную структуру разметки и выдает полезные сообщения об ошибках в случае неправильного форматирования.
Обновления хода выполнения в режиме реального времени: предоставляет обновления хода выполнения в режиме реального времени во время преобразования, показывая, какие задачи обрабатываются.
Преобразование задач Markdown в команды MCP
Инструмент convert_task_markdown обрабатывает структурированные файлы разметки и генерирует совместимый с MCP JSON:
Формат запроса:
{
"tool": "convert_task_markdown",
"arguments": {
"markdownPath": "/path/to/tasks.md",
"outputPath": "/path/to/output.json" // optional
}
}Формат ответа:
{
"tasksCount": 5,
"outputPath": "/path/to/output.json",
"tasks": [
{
"tool": "claude_code",
"arguments": {
"command": "cd /project && source .venv/bin/activate\n\nTASK TYPE: Validation...",
"dangerously_skip_permissions": true,
"timeout_ms": 300000
}
}
// ... more tasks
]
}Формат файла задачи Markdown
Файлы разметки задач должны иметь следующую структуру:
# Task 001: Task Title
## Objective
Clear description of what needs to be accomplished.
## Requirements
1. [ ] First requirement
2. [ ] Second requirement
## Tasks
### Module or Component Name
- [ ] Validate `path/to/file.py`
- [ ] Step 1
- [ ] Step 2
- [ ] Step 3Преобразователь будет:
Разбор структуры разметки
Извлечение метаданных и требований задачи
Создавайте подробные подсказки для каждой задачи проверки
Включите правильную настройку рабочего каталога
Добавить сводки проверки и завершения
Пример использования
Создайте файл задачи (
tasks/api_validation.md):
# Task 001: API Endpoint Validation
## Objective
Validate all API endpoints work with real database connections.
## Requirements
1. [ ] All endpoints must use real database
2. [ ] No mock data in validation
## Core API Tasks
- [ ] Validate `api/users.py`
- [ ] Change directory to project and activate .venv
- [ ] Test user creation endpoint
- [ ] Test user retrieval endpoint
- [ ] Verify JSON responsesПреобразовать в задачи MCP :
{
"tool": "convert_task_markdown",
"arguments": {
"markdownPath": "/project/tasks/api_validation.md"
}
}Конвертер показывает прогресс в реальном времени :
[Progress] Loading task file... [Progress] Validating markdown structure... [Progress] Converting 27 validation tasks... [Progress] Task 1/27: Converting core/constants.py [Progress] Task 2/27: Converting core/arango_setup.py ... [Progress] Conversion complete!Преобразователь преобразует общие инструкции в точные команды :
«Изменить каталог для проекта и активировать .venv» становится:
cd /home/user/project && source .venv/bin/activateВсе пути преобразуются в абсолютные пути.
Все команды полностью выполнимы и не допускают двусмысленности.
Выполнение преобразованных задач : возвращенные задачи содержат точные исполняемые команды и могут быть выполнены последовательно с помощью инструмента
claude_code.
Полный пример: от уценки до исполнения
Шаг 1: Пользователь создает файл задачи разметки ( project_tasks.md ):
# Task 001: Setup Development Environment
## Objective
Initialize the development environment with all dependencies.
## Requirements
1. [ ] Python 3.11+ installed
2. [ ] Virtual environment created
## Tasks
- [ ] Validate `setup.py`
- [ ] Change to project directory
- [ ] Create virtual environment
- [ ] Install dependenciesШаг 2: Пользователь подсказывает Клоду :
Use convert_task_markdown to process /home/user/project_tasks.mdШаг 3: MCP преобразует и проверяет :
Если формат правильный: возвращает исполняемый JSON
Если формат неверный: возвращает ошибку с инструкциями
Шаг 4: Результат (в случае успеха) :
[
{
"tool": "claude_code",
"arguments": {
"prompt": "cd /home/user/project && python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt",
"workFolder": "/home/user/project"
}
}
]Шаг 5: Клод может выполнять каждую задачу последовательно.
Проверка формата и обработка ошибок
Конвертер задач применяет определенную структуру разметки, чтобы обеспечить согласованное и надежное преобразование задач. Если ваш файл разметки неправильно отформатирован, конвертер выдает полезные сообщения об ошибках:
Пример ответа об ошибке:
{
"status": "error",
"error": "Markdown format validation failed",
"details": "Markdown format validation failed:\n - Missing required title. Format: '# Task NNN: Title'\n - Missing or empty 'Requirements' section. Format: '## Requirements\\n1. [ ] Requirement'\n - No validation tasks found. Format: '- [ ] Validate `module.py`' with indented steps\n\nRequired markdown format:\n# Task NNN: Title\n## Objective\nClear description\n## Requirements\n1. [ ] First requirement\n## Task Section\n- [ ] Validate `file.py`\n - [ ] Step 1\n - [ ] Step 2",
"helpUrl": "https://github.com/grahama1970/claude-code-mcp-enhanced/blob/main/README.md#markdown-task-file-format"
}Валидация гарантирует:
Присутствуют обязательные разделы (Название, Цель, Требования)
Задачи используют правильный формат флажков
Каждая задача имеет отступы шагов
Требования используют формат флажков для обеспечения согласованности
🦚 Шаблоны оркестровки задач
Этот сервер MCP поддерживает мощные возможности оркестровки задач для эффективной обработки сложных рабочих процессов.
Узор бумеранга (Claude Desktop ⟷ Claude Code)
Шаблон Boomerang позволяет Claude Desktop организовывать задачи и делегировать их Claude Code. Это позволяет вам:
Разбейте сложные рабочие процессы на более мелкие, управляемые подзадачи
Передача контекста из родительских задач в подзадачи
Получите результаты обратно из подзадач в родительскую задачу
Выбирайте между подробными или обобщенными результатами
Отслеживайте и управляйте прогрессом с помощью структурированных списков задач
Визуализация модели бумеранга
Вот простая схема, показывающая, как Клод разбивает задачу рецепта на шаги и делегирует их Клоду Коду:
graph TB
User("👨🍳 User")
Claude("🤖 Claude (Parent)")
Code1("🧁 Claude Code")
Code2("🧁 Claude Code")
User-->|"Make chocolate cake"| Claude
Claude-->|"Task 1: Find recipe"| Code1
Code1-->|"Result: Recipe found"| Claude
Claude-->|"Task 2: Convert measurements"| Code2
Code2-->|"Result: Measurements converted"| Claude
Claude-->|"Complete recipe + instructions"| UserВ этом примере:
Пользователь просит Клода приготовить рецепт шоколадного торта.
Клод (родитель) разбивает это на отдельные задачи
Клод делегирует задачу «Найти рецепт» Клоду Коду с идентификатором родительской задачи
Клод Код возвращает Клоду информацию о рецепте
Клод делегирует задачу «Преобразовать измерения» Клоду Коду
Клод Код возвращает преобразованные измерения
Клод объединяет все результаты и представляет пользователю полное решение.
Примеры простых задач:
Задание 1 — Найти рецепт:
{
"toolName": "claude_code:claude_code",
"arguments": {
"prompt": "Search for a classic chocolate cake recipe. Find one with good reviews.",
"parentTaskId": "cake-recipe-123",
"returnMode": "summary",
"taskDescription": "Find Chocolate Cake Recipe"
}
}Задача 2 — Преобразование измерений:
{
"toolName": "claude_code:claude_code",
"arguments": {
"prompt": "Convert the measurements in this recipe from cups to grams:\n\n- 2 cups flour\n- 1.5 cups sugar\n- 3/4 cup cocoa powder",
"parentTaskId": "cake-recipe-123",
"returnMode": "summary",
"taskDescription": "Convert Recipe Measurements"
}
}Как это работает
Создание подзадачи:
Создайте уникальный идентификатор задачи в родительской задаче.
Отправьте запрос инструменту
claude_codeс:Ваш конкретный запрос
Идентификатор родительской задачи
Описание задачи
Желаемый режим возврата («краткий» или «полный»)
Получение результатов:
Результат подзадачи будет включать специальный маркер:
<!-- BOOMERANG_RESULT {...} -->Этот маркер содержит JSON с метаданными задачи.
Родительская задача может проанализировать это, чтобы определить завершенные подзадачи.
Пример рабочего процесса с Claude Desktop:
You: I need to refactor this codebase. It's quite complex.
Claude Desktop: I'll help you with that. Let me break this down into smaller tasks for Claude Code to handle:
1. First, I'll have Claude Code analyze the codebase structure
2. Then, I'll have it identify problematic patterns
3. Finally, I'll ask it to generate a refactoring plan
[Claude Desktop sends a request to the claude_code tool with parentTaskId="task1" and returnMode="summary"]
[Claude Code analyzes the codebase and returns a summary with the BOOMERANG_RESULT marker]
Claude Desktop: Based on Claude Code's analysis, here are the key issues found:
- Duplicate code in modules X and Y
- Poor separation of concerns in module Z
- Inconsistent naming conventions
Now I'll ask Claude Code to suggest specific refactorings...Такой подход особенно полезен для сложных задач, требующих глубокого анализа или многоэтапного выполнения.
Пример комплексного управления списком задач
Вот подробный пример использования Claude с Claude Code MCP для управления и выполнения структурированного списка задач:
1. Настройка структуры списка задач
Сначала создайте файл списка задач (например, tasks.md ) со следующей структурой:
# Project Task List
## Parent Task: API Optimization Project
- [ ] Optimize API performance for high-traffic endpoints
- [ ] Analyze current API performance and identify bottlenecks
- [ ] Implement database query optimization for user endpoints
- [ ] Add Redis caching for frequently accessed data
- [ ] Set up performance monitoring
## Assumptions and Decisions
- [2025-05-15] Assumption: Redis is available in the infrastructure
- [2025-05-15] Decision: Focus on user endpoints first (Rationale: Highest traffic area)
## Relevant Files
- `src/controllers/userController.js`: User API endpoints
- `src/services/userService.js`: Business logic for user operations
## Improvement Notes
- Pattern identified: N+1 query issue in user listing endpoint
- Automation opportunity: Add caching automatically for all get-by-id endpoints2. Выполнение списка задач
Теперь Клод может систематически выполнять задания, используя Claude Code:
You: Please help me execute the task list in tasks.md, starting with the first subtask.
Claude: I'll help you work through your task list systematically. Let me first check the current task list to identify the next task to work on.
[Claude uses claude_code to read the task list]
I see the first subtask is "Analyze current API performance and identify bottlenecks". I'll execute this task now using Claude Code.
[Claude sends the following request to claude_code]:
{
"toolName": "claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Analysis\nTASK ID: api-perf-analysis\nCURRENT SUBTASK: Analyze current API performance and identify bottlenecks\n\nCONTEXT:\n- Parent task goal: Optimize API performance for high-traffic endpoints\n- This is the first step in our optimization process\n- Focus on user endpoints as noted in assumptions\n\nINSTRUCTIONS:\n1. Analyze the current API implementation in src/controllers/userController.js and src/services/userService.js\n2. Run performance tests on the user endpoints\n3. Identify specific bottlenecks and performance issues\n4. Document findings in a clear, structured format\n5. Update task list file after completion\n\nAfter completion, provide summary in this format:\n\nCOMPLETION SUMMARY:\n- What was done:\n- Results:\n- Files analyzed:\n- Issues identified:\n- Recommendations:\n- Next subtask in list:",
"workFolder": "/path/to/project"
}
}
[Claude Code executes the analysis task and returns results]
Great! Claude Code has completed the analysis. Here's what was found:
1. Main performance bottlenecks identified:
- N+1 query problem in the user listing endpoint
- Missing indexes on frequently queried fields
- No caching for repetitive data lookups
2. Recommendations:
- Add eager loading for user relationships
- Create database indexes for user_id and email fields
- Implement Redis caching with a 5-minute TTL
Let me update the task list to mark this task as complete and proceed to the next one.
[Claude uses claude_code to update the task list]:
{
"toolName": "claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Task List Update\n\n1. Read the current task list in tasks.md\n2. Mark the 'Analyze current API performance and identify bottlenecks' subtask as [x]\n3. Add new findings to the Improvement Notes section\n4. Add any new relevant files identified during analysis\n5. Write updated task list\n6. Return the updated task list",
"workFolder": "/path/to/project"
}
}
[Claude Code updates the task list and marks the first subtask complete]
I've updated the task list. The first subtask is now complete, and I've added the detailed findings to the Improvement Notes section. The next subtask is "Implement database query optimization for user endpoints".
Would you like me to proceed with this next subtask now?3. Продолжение последующих задач
Получив подтверждение, Клод перешел к следующей подзадаче:
You: Yes, please proceed with the next subtask.
Claude: I'll now execute the next subtask: "Implement database query optimization for user endpoints". This will involve fixing the N+1 query problem identified in the analysis and adding appropriate database indexes.
[Claude sends the following request to claude_code]:
{
"toolName": "claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Code Implementation\nTASK ID: db-query-optimization\nCURRENT SUBTASK: Implement database query optimization for user endpoints\n\nCONTEXT:\n- Parent task goal: Optimize API performance for high-traffic endpoints\n- Previous subtask identified N+1 query issues and missing indexes\n- Need to implement eager loading and proper indexes\n\nINSTRUCTIONS:\n1. Modify src/controllers/userController.js to implement eager loading for related data\n2. Add appropriate database indexes to user-related tables\n3. Refactor any inefficient database queries in userService.js\n4. Ensure changes maintain existing functionality\n5. Run tests to verify performance improvements\n6. Update task list file after completion\n\nAfter completion, provide summary in this format:\n\nCOMPLETION SUMMARY:\n- What was done:\n- Results:\n- Files modified:\n- Performance improvements:\n- Next subtask in list:",
"workFolder": "/path/to/project"
}
}
[Claude Code implements the optimizations and returns results]
Excellent! The database query optimizations have been successfully implemented. Here's a summary:
1. Changes made:
- Added eager loading in userController.js for user relationships
- Created new database indexes for user_id and email fields
- Refactored list query to use a single efficient JOIN statement
- Added pagination to prevent large result sets
2. Performance results:
- User listing endpoint response time reduced by 68%
- Database query count reduced from 25+ to 3 for typical requests
Let me update the task list again to reflect this progress.
[Claude uses claude_code to update the task list again]:
{
"toolName": "claude_code",
"arguments": {
"prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Task List Update\n\n1. Read the current task list in tasks.md\n2. Mark the 'Implement database query optimization for user endpoints' subtask as [x]\n3. Add new files modified to the Relevant Files section\n4. Update Improvement Notes with performance metrics\n5. Write updated task list\n6. Return the updated task list",
"workFolder": "/path/to/project"
}
}
[Claude Code updates the task list and marks the second subtask complete]
I've updated the task list again. Two subtasks are now complete, and the next one is "Add Redis caching for frequently accessed data". Would you like me to continue with this subtask?Такой структурированный подход позволяет Клоду систематически работать со сложными списками задач, сохраняя при этом четкое документирование прогресса, предположений и соответствующих файлов на протяжении всего процесса.
🎭 Паттерн самоорганизации (Клод Код в роли оркестратора)
Хотя Claude Desktop часто используется как родительский агент, вы можете использовать сам Claude Code как оркестратор и исполнитель. Такой подход создает автономную систему, в которой Claude Code управляет собственной оркестровкой задач, не требуя Claude Desktop.
graph TB
User("👨💻 User")
ClaudeCode("🤖 Claude Code\nOrchestrator")
ClaudeCodeSubtask1("⚙️ Claude Code\nSubtask 1")
ClaudeCodeSubtask2("⚙️ Claude Code\nSubtask 2")
User-->|"Complex project request"| ClaudeCode
ClaudeCode-->|"1. Plans tasks"| ClaudeCode
ClaudeCode-->|"2. Executes subtask 1"| ClaudeCodeSubtask1
ClaudeCodeSubtask1-->|"3. Returns result"| ClaudeCode
ClaudeCode-->|"4. Executes subtask 2"| ClaudeCodeSubtask2
ClaudeCodeSubtask2-->|"5. Returns result"| ClaudeCode
ClaudeCode-->|"6. Final solution"| UserЭтапы внедрения
Создайте входной скрипт , который инициализирует структуру вашей задачи и запускает Claude Code в качестве оркестратора.
Разработайте структуру данных задачи (обычно в формате JSON), которая отслеживает статус задачи и зависимости.
Создание сценариев исполнителя задач для обработки отдельных задач и обновления состояния задач.
Основные преимущества самоорганизации
Автономность : не требуется внешний оркестратор (вроде Claude Desktop)
Постоянное состояние : вся информация о задачах хранится в файлах JSON.
Восстановление после ошибки : можно возобновить выполнение последней успешной задачи в случае прерывания.
Упрощенное управление зависимостями : единая система управляет всеми взаимодействиями Claude Code
Автоматизация сценариев оболочки : легко интегрируется в конвейеры CI/CD или автоматизированные рабочие процессы.
Подробное руководство по внедрению с примерами сценариев и структурами задач см. в разделе Самоорганизация с Клодом Кодом .
👓 Интеграция режимов Roo
Этот сервер MCP поддерживает интеграцию со специализированными режимами через файл конфигурации .roomodes . При включении вы можете указать, какой режим использовать для каждой задачи, что позволяет реализовать специализированное поведение.
Как использовать режимы Roo
Включить поддержку режима Roo:
Установите переменную среды
MCP_USE_ROOMODES=trueв конфигурации MCPСоздайте файл
.roomodesв корневом каталоге вашего сервера MCP.При желании можно включить горячую перезагрузку с помощью
MCP_WATCH_ROOMODES=trueдля автоматической перезагрузки конфигурации при изменении файла.
Настройте свои режимы:
Файл
.roomodesдолжен содержать объект JSON с массивомcustomModesКаждый режим должен иметь
slug,name,roleDefinitionи, опционально,apiConfigurationсmodelId
Использование режима:
При создании запросов к инструменту
claude_codeвключите параметрmodeс обозначением желаемого режима.Сервер MCP автоматически применит определение роли и конфигурацию модели.
Пример файла .roomodes:
{ "customModes": [ { "slug": "coder", "name": "💻 Coder", "roleDefinition": "You are a coding specialist who writes clean, efficient code.", "apiConfiguration": { "modelId": "claude-3-sonnet-20240229" } }, { "slug": "designer", "name": "🎨 Designer", "roleDefinition": "You are a design specialist focused on UI/UX solutions." } ] }Пример конфигурации среды:
{ "mcpServers": { "claude-code-mcp-enhanced": { "command": "npx", "args": ["github:grahama1970/claude-code-mcp-enhanced"], "env": { "MCP_USE_ROOMODES": "true", "MCP_WATCH_ROOMODES": "true", "MCP_CLAUDE_DEBUG": "false" } } } }Выполнение запросов с режимами:
{ "toolName": "claude_code:claude_code", "arguments": { "prompt": "Your work folder is /path/to/project\n\nCreate unit tests for the user authentication module.", "workFolder": "/path/to/project", "mode": "coder" } }
Основные характеристики Roo Modes:
Специализированное поведение : разные режимы могут иметь разные системные подсказки и конфигурации моделей.
Горячая перезагрузка : если
MCP_WATCH_ROOMODES=true, сервер автоматически перезагружает конфигурацию при изменении файла.roomodesПроизводительность : сервер кэширует конфигурацию roomodes для повышения производительности.
Резервный вариант : если режим не найден или румоды отключены, сервер продолжает работу с поведением по умолчанию.
🛠️ Улучшенные характеристики надежности
Этот сервер включает в себя несколько улучшений для повышения надежности и производительности:
1. Предотвращение сердцебиения и тайм-аута
Чтобы предотвратить тайм-ауты на стороне клиента во время длительных операций:
Добавлен настраиваемый механизм пульсации, который отправляет обновления хода выполнения каждые 15 секунд.
Реализовано отслеживание времени выполнения и отчетность
Добавлены настраиваемые параметры тайм-аута через переменные среды.
2. Надежная обработка ошибок с повторными попытками
Добавлена интеллектуальная логика повтора для временных ошибок:
Реализован автоматический повтор с настраиваемыми параметрами
Добавлена классификация ошибок для определения повторяющихся проблем.
Созданы подробные отчеты об ошибках и отслеживание
3. Система отслеживания запросов
Реализовано комплексное управление жизненным циклом запросов:
Добавлены уникальные идентификаторы для каждого запроса
Создано отслеживание для текущих запросов
Обеспечивает надлежащую очистку после завершения или сбоя
4. Плавное выключение
Добавлена правильная обработка завершения процесса:
Реализованы обработчики сигналов для SIGINT и SIGTERM.
Добавлено отслеживание текущих запросов.
Создана логика ожидания для чистого завершения работы
Обеспечивает надлежащую уборку на выходе
5. Кэширование конфигурации и горячая перезагрузка
Добавлена оптимизация производительности для конфигурации:
Реализовано кэширование для файла roomodes
Добавлена автоматическая аннуляция на основе изменений файла.
Создан настраиваемый механизм наблюдения за файлами
⚙️ Параметры конфигурации
Поведение сервера можно настроить с помощью следующих переменных среды:
Переменная | Описание | По умолчанию |
| Абсолютный путь к исполняемому файлу CLI Claude | Автоматическое определение |
| Включить подробное ведение журнала отладки |
|
| Интервал между отчетами о ходе работ | 15000 (15с) |
| Тайм-аут для выполнения CLI | 1800000 (30м) |
| Максимальное количество попыток повтора для временных ошибок | 3 |
| Задержка между повторными попытками | 1000 (1с) |
| Включить интеграцию режимов Roo |
|
| Автоматическая перезагрузка .roomodes при изменениях |
|
Их можно задать в вашей оболочке или в блоке env конфигурации вашего сервера mcp.json .
📸 Наглядные примеры
Вот несколько наглядных примеров работы сервера:
Исправление настройки ESLint
Вот пример использования инструмента Claude Code MCP для интерактивного исправления настройки ESLint путем удаления старых файлов конфигурации и создания новых:
Пример листинга файлов
Вот пример инструмента Claude Code, выводящего список файлов в каталоге:
Сложные многоэтапные операции
В этом примере показано, как claude_code обрабатывает более сложную многошаговую задачу, например, подготовку релиза путем создания ветки, обновления нескольких файлов ( package.json , CHANGELOG.md ), внесения изменений и инициирования запроса на извлечение — все это в рамках одной последовательной операции.
Исправление рабочего процесса действий GitHub
🎯 Основные варианты использования
Этот сервер, через свой унифицированный инструмент claude_code , открывает широкий спектр мощных возможностей, предоставляя вашему ИИ прямой доступ к Claude Code CLI. Вот несколько примеров того, чего вы можете достичь:
Генерация кода, анализ и рефакторинг:
"Generate a Python script to parse CSV data and output JSON.""Analyze my_script.py for potential bugs and suggest improvements."
Операции с файловой системой (создание, чтение, редактирование, управление):
Создание файлов:
"Your work folder is /Users/steipete/my_project\n\nCreate a new file named 'config.yml' in the 'app/settings' directory with the following content:\nport: 8080\ndatabase: main_db"Редактирование файлов:
"Your work folder is /Users/steipete/my_project\n\nEdit file 'public/css/style.css': Add a new CSS rule at the end to make all 'h2' elements have a 'color: navy'."Перемещение/Копирование/Удаление:
"Your work folder is /Users/steipete/my_project\n\nMove the file 'report.docx' from the 'drafts' folder to the 'final_reports' folder and rename it to 'Q1_Report_Final.docx'."
Контроль версий (Git):
"Your work folder is /Users/steipete/my_project\n\n1. Stage the file 'src/main.java'.\n2. Commit the changes with the message 'feat: Implement user authentication'.\n3. Push the commit to the 'develop' branch on origin."
Выполнение команд терминала:
"Your work folder is /Users/steipete/my_project/frontend\n\nRun the command 'npm run build'.""Open the URL https://developer.mozilla.org in my default web browser."
Поиск в Интернете и обобщение:
"Search the web for 'benefits of server-side rendering' and provide a concise summary."
Сложные многоэтапные рабочие процессы:
Автоматизируйте повышение версии, обновление журналов изменений и выпуски тегов:
"Your work folder is /Users/steipete/my_project\n\nFollow these steps: 1. Update the version in package.json to 2.5.0. 2. Add a new section to CHANGELOG.md for version 2.5.0 with the heading '### Added' and list 'New feature X'. 3. Stage package.json and CHANGELOG.md. 4. Commit with message 'release: version 2.5.0'. 5. Push the commit. 6. Create and push a git tag v2.5.0."
Исправление файлов с синтаксическими ошибками:
"Your work folder is /path/to/project\n\nThe file 'src/utils/parser.js' has syntax errors after a recent complex edit that broke its structure. Please analyze it, identify the syntax errors, and correct the file to make it valid JavaScript again, ensuring the original logic is preserved as much as possible."
Взаимодействие с GitHub (например, создание запроса на извлечение):
"Your work folder is /Users/steipete/my_project\n\nCreate a GitHub Pull Request in the repository 'owner/repo' from the 'feature-branch' to the 'main' branch. Title: 'feat: Implement new login flow'. Body: 'This PR adds a new and improved login experience for users.'"
Взаимодействие с GitHub (например, проверка статуса PR CI):
"Your work folder is /Users/steipete/my_project\n\nCheck the status of CI checks for Pull Request #42 in the GitHub repository 'owner/repo'. Report if they have passed, failed, or are still running."
ВАЖНО: Не забудьте указать контекст текущего рабочего каталога (CWD) в приглашениях для операций файловой системы или git (например, "Your work folder is /path/to/project\n\n...your command..." ).
🔧 Устранение неполадок
"Команда не найдена" (claude-code-mcp): Если установлено глобально, убедитесь, что глобальный каталог bin npm находится в системной переменной PATH. Если используется
npx, убедитесь, что самnpxработает."Команда не найдена" (claude или ~/.claude/local/claude): Убедитесь, что Claude CLI установлен правильно. Запустите
claude/doctorили проверьте его документацию.Проблемы с разрешениями: убедитесь, что вы выполнили шаг «Важный шаг первоначальной настройки».
Ошибки JSON с сервера: если
MCP_CLAUDE_DEBUGимеетtrue, сообщения об ошибках или журналы могут помешать анализу JSON MCP. Установите значениеfalseдля нормальной работы.Ошибки ESM/импорта: убедитесь, что вы используете Node.js v20 или более позднюю версию.
Клиентские тайм-ауты: для длительных операций сервер отправляет сообщения heartbeat каждые 15 секунд, чтобы предотвратить клиентские тайм-ауты. Если тайм-ауты все еще возникают, вы можете настроить интервал heartbeat с помощью переменной среды
MCP_HEARTBEAT_INTERVAL_MS.Ошибки сети/сервера: сервер теперь включает автоматическую логику повтора для временных ошибок. Если у вас все еще возникают проблемы, попробуйте увеличить значения
MCP_MAX_RETRIESиMCP_RETRY_DELAY_MS.Предупреждение о возврате Claude CLI: Если вы видите предупреждение о том, что Claude CLI не найден в ~/.claude/local/claude, это нормально. Сервер возвращается к использованию команды
claudeиз вашего PATH. Вы можете задать переменную средыCLAUDE_CLI_PATH, чтобы указать точный путь к исполняемому файлу Claude CLI, если это необходимо.
👨💻 Для разработчиков: локальная настройка и участие
Если вы хотите разработать этот сервер или внести в него свой вклад, или запустить его из клонированного репозитория для тестирования, ознакомьтесь с нашим Руководством по локальной установке и настройке разработки .
💪 Вклад
Вклады приветствуются! Пожалуйста, обратитесь к Руководству по локальной установке и настройке разработки для получения подробной информации о настройке вашей среды.
Отправляйте проблемы и запросы на извлечение в репозиторий GitHub .
⚖️ Лицензия
Массачусетский технологический институт
💬 Отзывы и поддержка
Если у вас возникли проблемы или есть вопросы по использованию сервера Claude Code MCP, пожалуйста:
Проверьте раздел «Устранение неполадок» выше.
Отправьте сообщение о проблеме в репозиторий GitHub
Присоединяйтесь к обсуждению в разделе обсуждений репозитория
Мы ценим ваши отзывы и вклад в улучшение этого инструмента!
Available Tools
3 toolsclaude_codeA
Claude Code Agent: Your versatile multi-modal assistant for code, file, Git, and terminal operations via Claude CLI. Use workFolder for contextual execution.
• File ops: Create, read, (fuzzy) edit, move, copy, delete, list files, analyze/ocr images, file content analysis └─ e.g., "Create /tmp/log.txt with 'system boot'", "Edit main.py to replace 'debug_mode = True' with 'debug_mode = False'", "List files in /src", "Move a specific section somewhere else"
• Code: Generate / analyse / refactor / fix └─ e.g. "Generate Python to parse CSV→JSON", "Find bugs in my_script.py"
• Git: Stage ▸ commit ▸ push ▸ tag (any workflow) └─ "Commit '/workspace/src/main.java' with 'feat: user auth' to develop."
• Terminal: Run any CLI cmd or open URLs └─ "npm run build", "Open https://developer.mozilla.org"
• Web search + summarise content on-the-fly
• Multi-step workflows (Version bumps, changelog updates, release tagging, etc.)
• GitHub integration Create PRs, check CI status
• Confused or stuck on an issue? Ask Claude Code for a second opinion, it might surprise you!
• Task Orchestration with "Boomerang" pattern └─ Break down complex tasks into subtasks for Claude Code to execute separately └─ Pass parent task ID and get results back for complex workflows └─ Specify return mode (summary or full) for tailored responses
Prompt tips
Be concise, explicit & step-by-step for complex tasks. No need for niceties, this is a tool to get things done.
For multi-line text, write it to a temporary file in the project root, use that file, then delete it.
If you get a timeout, split the task into smaller steps.
Seeking a second opinion/analysis: If you're stuck or want advice, you can ask
claude_codeto analyze a problem and suggest solutions. Clearly state in your prompt that you are looking for analysis only and no actual file modifications should be made.If workFolder is set to the project path, there is no need to repeat that path in the prompt and you can use relative paths for files.
Claude Code is really good at complex multi-step file operations and refactorings and faster than your native edit features.
Combine file operations, README updates, and Git commands in a sequence.
Task Orchestration: For complex workflows, use
parentTaskIdto create subtasks andreturnMode: "summary"to get concise results back.Claude can do much more, just ask it!
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | When MCP_USE_ROOMODES=true, specifies the mode from .roomodes to use (e.g., "boomerang-mode", "coder", "designer", etc.). | |
| parentTaskId | No | Optional ID of the parent task that created this task (for task orchestration/boomerang). | |
| prompt | Yes | The detailed natural language prompt for Claude to execute. | |
| returnMode | No | How results should be returned: summary (concise) or full (detailed). Defaults to full. | |
| taskDescription | No | Short description of the task for better organization and tracking in orchestrated workflows. | |
| workFolder | No | Mandatory when using file operations or referencing any file. The working directory for the Claude CLI execution. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It does an excellent job describing the tool's capabilities, constraints (workFolder requirement, timeout handling), and operational patterns (boomerang orchestration, return modes). However, it doesn't explicitly mention authentication requirements, rate limits, or error handling specifics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is excessively long (over 500 words) with redundant information, marketing language ('it might surprise you!'), and tips that belong in documentation rather than a tool description. While well-structured with bullet points, it violates the principle that every sentence should earn its place in a tool description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex 6-parameter tool with no annotations and no output schema, the description provides substantial context about capabilities, constraints, and usage patterns. However, the lack of output schema means the description should ideally explain what kind of results to expect, which it only partially addresses through returnMode discussion.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 6 parameters thoroughly. The description references parameters like workFolder, parentTaskId, and returnMode in context, but doesn't add significant semantic value beyond what's already in the schema descriptions. The baseline of 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states this is a 'versatile multi-modal assistant for code, file, Git, and terminal operations via Claude CLI' with specific examples of each capability. It distinguishes itself from sibling tools (convert_task_markdown, health) by being a comprehensive execution tool rather than a conversion or health check utility.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides extensive guidance on when and how to use the tool, including explicit 'Prompt tips' with 9 specific recommendations, examples for different operation types, and guidance on task orchestration. It clearly distinguishes between analysis-only requests and execution requests in tip #4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
convert_task_markdownB
Converts markdown task files into Claude Code MCP-compatible JSON format. Returns an array of tasks that can be executed using the claude_code tool.
| Name | Required | Description | Default |
|---|---|---|---|
| markdownPath | Yes | Path to the markdown task file to convert. | |
| outputPath | No | Optional path where to save the JSON output. If not provided, returns the JSON directly. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the return value (array of tasks) and output behavior (saving or returning JSON), but doesn't cover critical aspects like error handling, file format requirements, or performance implications. For a tool with no annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with the core purpose in the first sentence, followed by a clear statement of the return value and usage context. Every sentence adds value without redundancy, making it efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and 2 parameters with full schema coverage, the description is minimally adequate. It covers the basic purpose and output but lacks details on behavioral traits, error cases, or integration with sibling tools. This meets the minimum viable threshold but has clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents both parameters. The description adds no additional parameter semantics beyond what the schema provides (e.g., it doesn't explain markdown file structure or JSON format details). Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: converting markdown task files to Claude Code MCP-compatible JSON format. It specifies the verb 'converts' and the resource 'markdown task files', and mentions the output format. However, it doesn't explicitly differentiate from sibling tools like 'claude_code' or 'health', which would require a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by stating the output can be executed using 'claude_code', suggesting a workflow. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., direct use of 'claude_code' or other conversion methods) or any prerequisites. This is adequate but has gaps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
healthA
Returns health status, version information, and current configuration of the Claude Code MCP server.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns health status, version, and configuration, which gives basic behavioral context. However, it lacks details on potential side effects, error handling, or performance characteristics, which would be useful for a monitoring tool. The description does not contradict any annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently conveys the tool's purpose without any wasted words. It is front-loaded with the key action ('Returns') and clearly lists the returned information, making it easy to understand at a glance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (0 parameters, no output schema, no annotations), the description is complete enough for its purpose. It explains what the tool returns, which is adequate for a simple health-check tool. However, without an output schema, adding a hint about the return format could slightly improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and schema description coverage is 100%, so there is no need for parameter documentation in the description. The baseline for 0 parameters is 4, as the description appropriately omits parameter details and focuses on the tool's purpose, which is sufficient given the lack of inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific verb ('Returns') and resource ('health status, version information, and current configuration of the Claude Code MCP server'), distinguishing it from sibling tools like 'claude_code' and 'convert_task_markdown' which likely perform different functions. It precisely defines what the tool does without being vague or tautological.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by specifying it returns server health and configuration, suggesting it should be used for monitoring or diagnostic purposes. However, it does not explicitly state when to use this tool versus alternatives or provide any exclusions, leaving some ambiguity about its specific application scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
3 tool updates
v1.0.0- First observed
claude_code - First observed
convert_task_markdown - First observed
health
TDQS
Scored across 3 tools
The three tools have clearly distinct purposes with no overlap: claude_code handles all code/file/Git/terminal operations, convert_task_markdown specifically converts markdown to JSON format, and health provides server status information. Each tool serves a unique function in the workflow.
The naming shows mixed conventions: claude_code uses snake_case but includes the server name, convert_task_markdown uses snake_case with a descriptive verb_noun pattern, and health is a simple noun. While readable, there's inconsistency in structure and verb usage across the set.
Three tools is reasonable for this enhanced code assistant server, though slightly minimal. The claude_code tool is comprehensive, covering multiple domains, while the other two provide essential supporting functions. A few more specialized tools might improve granularity, but the current count works.
The tool surface covers core code assistant workflows well through the comprehensive claude_code tool, with supporting tools for task conversion and health checks. Minor gaps exist in specialized operations like dedicated Git branch management or isolated terminal command execution, but agents can work around these using the versatile claude_code tool.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables Claude to manage software development projects with complete context awareness and code execution through Docker environments.11 npm4-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that allows Claude AI to interact with custom tools, enabling extension of Claude's capabilities through the MCP framework.-
- AlicenseNot gradedqualityFmaintenanceAn enhanced Model Context Protocol server that enables Claude to seamlessly collaborate with multiple AI models (Gemini, OpenAI, local models) for code analysis and development tasks, maintaining context across conversations.55 npm54Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA customizable Model Context Protocol server built with mcp-framework that enables Claude to access external tools and capabilities through a standardized interface.55 npm-