Quality Clouds Hub

SSE

by qualityclouds

302 downloads Not rated yet

About

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

Details

Transport
SSE

Explore

- Remote server (Streamable HTTP): https://api.qualityclouds.ai/mcp, no local install
- Stack detection: rulesets activate automatically for the detected stack, across six functional areas: Security, Performance, Scalability, Manageability, Maintainability and Architecture
- Rules target the mistakes AI tools actually make: exposed service-role keys, hardcoded credentials, missing error checks on mutations, client-side JWT decoding, missing rate limiting
- Every session is recorded: rules verified, violations fixed (file and lines), violations prevented, and which model did the work
- Repository Production-Ready Score in your workspace at portal.qualityclouds.ai
- Works with Cursor, Claude Code, Lovable, Replit and any MCP-compatible client

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Quality Clouds Hub
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Sign up at portal.qualityclouds.ai (one click, permanent free tier), generate an API key on the MCP Connections page, and add the remote server to your client. Working config snippets for Claude Code and Cursor are in the repository README.

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…

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, ve…

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_to…

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "quality clouds hub": {
            "qualityclouds-hub": {
                "url": "https://api.qualityclouds.ai/mcp",
                "headers": {
                    "Authorization": "Bearer YOUR_API_KEY"
                }
            }
        }
    }
}

McpServers

{
    "qualityclouds-hub": {
        "url": "https://api.qualityclouds.ai/mcp",
        "headers": {
            "Authorization": "Bearer YOUR_API_KEY"
        }
    }
}

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

Quality Clouds Hub connects your AI development tool to a governance rule library built around the error patterns AI-generated code typically contains. When the model generates code, the rules for your detected stack are already in its context, so the output follows them from the first line.

- Remote server (Streamable HTTP): https://api.qualityclouds.ai/mcp
- Auth: API key, generated in one click at portal.qualityclouds.ai. Permanent free tier.
- Works with Cursor, Claude Code, Lovable, Replit and any MCP-compatible client
- Stacks covered: TypeScript, Python, Java, Node, React, Supabase and more

What it does

Rulesets are stack-specific and activate automatically for the stack the server detects. A single repository scan activates rulesets across six functional areas: Security, Performance, Scalability, Manageability, Maintainability and Architecture. The Supabase ruleset alone covers 12 rules, including no service-role keys outside the server, no hardcoded keys or project URLs, mandatory error checks on every mutation, no client-side JWT decoding, and rate limiting on edge functions.

The server exposes three tools:

| Tool | What it does |
|------|--------------|
| get_tools | Detects your project's stack and returns the applicable governance tooling |
| get_rules_for_tool | Returns the active ruleset, rule by rule, with IDs |
| register_applied_actions | Records what was done: rules verified compliant, violations fixed (file and lines), violations prevented during generation, and which model did the work |

Every session produces a structured record of what was checked, fixed and prevented. Your repository's Production-Ready Score and full findings live in your workspace at portal.qualityclouds.ai.

Try it in 5 minutes (Claude Code)

1. Sign up and generate an API key at portal.qualityclouds.ai (MCP Connections page).
2. Add the server:

claude mcp add --scope user --transport http qualityclouds-hub https://api.qualityclouds.ai/mcp \
  --header "Authorization: Bearer <your-api-key>"

3. Check it connected:

claude mcp list

4. Open a session in any repo and ask Claude Code to review a file against your coding standards. It will detect the Hub server, fetch the rules for your stack, and register the results back to your workspace.

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "qualityclouds-hub": {
      "url": "https://api.qualityclouds.ai/mcp",
      "headers": { "Authorization": "Bearer <your-api-key>" }
    }
  }
}

Links

- Sign up: portal.qualityclouds.ai
- Product: qualityclouds.ai/hub
- Community, docs and support: github.com/qualityclouds/Community

Built by Quality Clouds, the AI Code Governance platform, governing 950+ enterprise platform instances since 2015.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.