Skip to content
Verified official

PatchLabs MCP

v3.1.0

dev.patchlabs/patchlabs

Security checks for AI-built apps (Lovable, Supabase, Bolt): RLS, headers, monitoring, fixes.

transport:streamable-http tools:6

Target client

run in your project directory

claude mcp add --transport http patchlabs https://api.patchlabs.dev/mcp

setup guides: Claude Code Claude Desktop Cursor VS Code Zed Windsurf Cline Gemini CLI Grok ChatGPT Claude.ai LangChain

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

rls_check

rls check

headers_check

headers check

start_check Mutating

start check

get_check Read-only

get check

list_apps Read-only

list apps

run_check Mutating

run check

All 6 tools, one page each

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. Check the server's own documentation before granting access.