Quality Clouds Hub

AI code governance rules injected into Cursor, Claude Code and other MCP clients at generation time.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • 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

What data it sees

Do you need an account

An API key from the service settings is required

AI code governance rules injected into Cursor, Claude Code and other MCP clients at generation time.

How to connect

How to connect Quality Clouds Hub to Claude

The server address to paste into Claude settings:

https://hub--qualityclouds.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Quality Clouds Hub to ChatGPT

The server address to paste into ChatGPT settings:

https://hub--qualityclouds.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Quality Clouds Hub to Cursor

The server address to paste into Cursor settings:

https://hub--qualityclouds.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (3)

Raw names from tools/list. Only developers need these.

get_rules_for_toolRetrieves 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_toolsProvides 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_actionsRegisters 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.