Quality Clouds Hub
AI code governance rules injected into Cursor, Claude Code and other MCP clients at generation time.
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетНужен API-ключГлобальныйБесплатноТолько чтение
Что умеет
- Get Rules For Tool: Retrieves the organization's coding standards and best practices rules for a tool. WHEN TO CALL: Before writing or modifying ANY code. You MUST call this after get_tools and before
- Get Tools: Provides the list of linting/coding tools for the project's tech stack. WHEN TO CALL: At the START of any coding task (new feature, bug fix, refactor, file edit). Also when the user asks to
- Register Applied Actions: Registers the actions you took to comply with the organization's rules. WHEN TO CALL: After completing ANY coding task where you consulted rules via get_rules_for_tool. CRITI
Какие данные видит
Нужен ли аккаунт
Нужен API-ключ из настроек сервиса
AI code governance rules injected into Cursor, Claude Code and other MCP clients at generation time.
Список инструментов сервера (3)
Технические названия из tools/list. Нужны только разработчикам.
| get_rules_for_tool | Retrieves the organization's coding standards and best practices rules for a tool. WHEN TO CALL: Before writing or modifying ANY code. You MUST call this after get_tools and before implementing changes. Do NOT skip this step — without it you cannot report compliance correctly. tool_id: MUST be one of the tool_id values returned by get_tools(). Do NOT guess or invent. Returns the ruleset with rule IDs. Each rule has an ID — you MUST use these exact IDs in register_applied_actions. Never use "N/A" or invent rule IDs. After completing your coding task, call register_applied_actions with rule_id values taken ONLY from this response (verified_compliant, violations_fixed, violations_prevented). |
| get_tools | Provides the list of linting/coding tools for the project's tech stack. WHEN TO CALL: At the START of any coding task (new feature, bug fix, refactor, file edit). Also when the user asks to fix compliance, apply rules, or align with standards. MANDATORY FLOW (do not skip steps): 1) get_tools first (this call) 2) get_rules_for_tool(tool_id) for EACH relevant tool_id from this response — NEVER skip this 3) Apply rules to your code, then call register_applied_actions Returns tool_id, name, version, ruleset_ids. Use ONLY the exact tool_id values from this response when calling get_rules_for_tool. Without get_rules_for_tool you cannot know the actual rules or their IDs, and you cannot correctly call register_applied_actions. |
| register_applied_actions | Registers the actions you took to comply with the organization's rules. WHEN TO CALL: After completing ANY coding task where you consulted rules via get_rules_for_tool. CRITICAL — rule_id: Every item (verified_compliant, violations_fixed, violations_prevented) MUST have rule_id set to an exact rule ID from the get_rules_for_tool response. NEVER use "N/A", "unknown", or invent rule IDs. If you did not call get_rules_for_tool, you cannot fill this correctly — call get_tools → get_rules_for_tool first, then report. STRUCTURE: llm_name and llm_version identify the model; verified_compliant (file_path, rule_id, comments); violations_fixed (file_path, rule_id, start_line, end_line, issue_description, fix_applied); violations_prevented (file_path, rule_id, comments). Rule-related fields in English. |