Skip to content
MCP server

VibeScale

Free pre-launch security checks for AI-built apps: leaked keys, Supabase RLS, env vars

Status and history

Answered our latest tool-list check 21 hours ago with 3 tools. It will be marked verified after 3 successful checks in 7 days.

Pricing
Free
Platforms
API
Runs
Remotely
Version
1.0.1
Listing updated
2 days ago

About VibeScale

VibeScale is a free MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

Apps generated with AI builders often ship with secrets in the browser bundle or database tables left open. VibeScale gives a chat assistant three free checks aimed at exactly those problems, and its page is written in Hebrew.

The live-site scan reads only what a site sends every visitor, reporting partly masked secret keys in browser code, published source code and missing protection headers, each with a fix. The Supabase checker reads migration SQL as text and flags tables without row-level security, permissive policies, anon write grants and public storage buckets, with corrective SQL. The environment check takes variable names and says whether the build tool ships each to the browser and whether it looks like a server-side key.

In Claude Code the tools can work directly on files in the project. The SQL is never run, no login is needed, and a site scan result is held in server memory for up to an hour to avoid rescanning.

Install

Run in a terminal

claude mcp add --transport http vibescale https://vibe.elya-studio.com/mcp

Add to Settings → Connectors → Add custom connector

https://vibe.elya-studio.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "vibescale": {
      "url": "https://vibe.elya-studio.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "vibescale": {
      "type": "http",
      "url": "https://vibe.elya-studio.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "vibescale": {
      "serverUrl": "https://vibe.elya-studio.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "vibescale": {
      "type": "http",
      "url": "https://vibe.elya-studio.com/mcp"
    }
  }
}

Tools this server provides (3)

Read directly from the server.

scan_app_launch_readiness
Reads one public web app the way a browser does (its HTML, the same-site scripts it loads and any source maps they point to) and reports what any visitor can already see: server secret keys shipped to the browser (Supabase service_role, OpenAI, Anthropic, Stripe, AWS, GitHub, SendGrid, Resend; shown masked), a published source map, no HTTPS, and missing Content-Security-Policy, HSTS or frame prote
lint_supabase_rls
Reads Supabase SQL (migrations or a schema dump) as text and lists tables in exposed schemas without row level security, RLS with no policy, policies that allow everything or read user_metadata, policies without a role, write grants to anon, SECURITY DEFINER functions and views, new tables without a grant, and public storage buckets, each with SQL that fixes it. Use when someone asks whether their
check_env_exposure
Takes environment variable NAMES (never values) and says, for each one, whether the build tool ships it to every visitor (VITE_, NEXT_PUBLIC_, EXPO_PUBLIC_, REACT_APP_, PUBLIC_, GATSBY_, NUXT_PUBLIC_) and whether its name looks like a server secret that must not be there. Use when someone asks whether their .env or API keys are exposed in a Lovable, Bolt, Vite, Next.js or Expo app. Send names only

What it does

Live site scan
Finds leaked keys, exposed source and missing headers visible to any visitor.
Supabase RLS linter
Flags missing RLS, permissive policies and public buckets, with fix SQL.
Env exposure check
Says which variables the build tool sends to the browser.
Read-only by design
Never logs in, touches the database or runs the SQL.
Free, no account
Connects with one URL and no keys.

Good for

  • Scan a deployed app for keys leaking into the browser
  • Review Supabase migrations for missing row-level security
  • Check an .env.example for variables that should stay server-side
  • Run a quick check before launching an AI-built app

Pricing

Free

Free tools, no sign-up

Prices change. Check vibe.elya-studio.com before you buy.

VibeScale FAQ

What is sent to the service?

Only what the tool needs: a site URL, the SQL text or variable names. Variable values are not needed and are deleted if sent.

Does it change my app?

No. All tools are read-only and the SQL is read as text, not executed.

How do I add it to Claude Code?

Run claude mcp add --transport http vibescale https://vibe.elya-studio.com/mcp.

What does a human pre-launch review add?

It is a manual look from the inside at permissions, keys, database, payments and hosting cost, which the tools cannot see.

Is VibeScale free?

Yes. VibeScale is free to use.

How do I add VibeScale to Claude Code?

Run this command in your terminal: claude mcp add --transport http vibescale https://vibe.elya-studio.com/mcp

What are the best alternatives to VibeScale?

The closest alternatives to VibeScale are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to VibeScale

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools