Skip to content
MCP server

GuardLayer

Security checks for Next.js and Supabase apps, run from your AI agent

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

About GuardLayer

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

GuardLayer targets a specific failure of AI-built apps: tables created in the Supabase dashboard, row-level security switched off by hand, and policies that look protective but pass for anyone who can sign up. Its check goes beyond reading code by also examining a snapshot of the live project.

The flow is split in three. One tool scans code the agent sends, looking for service role keys in client code or NEXT_PUBLIC_ and VITE_ variables, missing or open RLS in migrations, and API routes, Server Actions and Edge Functions that never check the caller. Another provides a read-only SQL query for catalog metadata only, with no rows. A third checks that snapshot along with Auth settings and, given the previous result's keys, reports what closed, what is new and what remains open.

The site says nothing sent is stored, and fixes go in a migration rather than turning RLS off.

Install

Run in a terminal

claude mcp add --transport http guardlayer https://www.guardlayer.io/api/mcp

Add to Settings → Connectors → Add custom connector

https://www.guardlayer.io/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "guardlayer": {
      "url": "https://www.guardlayer.io/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "guardlayer": {
      "type": "http",
      "url": "https://www.guardlayer.io/api/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "guardlayer": {
      "serverUrl": "https://www.guardlayer.io/api/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "guardlayer": {
      "type": "http",
      "url": "https://www.guardlayer.io/api/mcp"
    }
  }
}

Tools this server provides (3)

Taken from the project documentation; the running server may differ.

scan_files
Static scan of code sent by the agent
get_supabase_snapshot_sql
Read-only SQL that reads the project's catalog
check_supabase_snapshot
Check a snapshot with Auth settings and compare to a prior result

What it does

Code scan
Flags leaked service keys, open RLS and unguarded routes with a fix for each.
Metadata-only snapshot
A read-only query returns catalog data, never table rows.
Live project check
Reviews policies, grants, buckets and Auth settings together.
Fix confirmation
Compares results to show which findings closed.
Plugin and skill
A Claude Code plugin adds a skill that tells the agent when to use it.

Good for

  • Review a Supabase project before deploying
  • Verify that a claimed fix actually closed a leak
  • Catch policies that only check for a signed-in user
  • Audit an AI-generated app for exposed service role keys

Pricing

Free

Described as free on its MCP page

Prices change. Check guardlayer.io before you buy.

GuardLayer FAQ

Does GuardLayer see my database or keys?

The site says no: your agent runs a read-only query returning catalog metadata and sends only that JSON.

Is anything stored?

The site says code and snapshots are checked in memory and discarded.

Is it free?

The page describes it as free.

Which clients can use it?

Claude Code, Cursor and any client supporting remote MCP over HTTP.

Is GuardLayer free?

Yes. GuardLayer is free to use.

How do I add GuardLayer to Claude Code?

Run this command in your terminal: claude mcp add --transport http guardlayer https://www.guardlayer.io/api/mcp

What are the best alternatives to GuardLayer?

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

Alternatives to GuardLayer

  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