MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Is your AI-built app safe to launch? A grade from A to F for Lovable, Bolt, v0 and Replit apps, with a fix prompt for every problem.
Apache-2.0 ★ 1 -
vibeauryonupdated this year
AI agent OS for vibe coders — MCP server for Claude, Cursor, Windsurf & Lovable. Security audits, SEO, performance, design tokens, copywriting and 76+ dev tools in one CLI.
npm MIT -
BDK Native plugin: connect your AI assistant to BDK's MCP server and turn a web app built with Lovable, Bolt, Replit, Bubble or any other tool into iOS and Android apps.
MIT -
The crash test for AI coding agents: 19 realistic traps for Claude Code, Codex and Gemini CLI in a sealed container, plus a safety grade with fix prompts for apps built with Lovable, Bolt, v0 and Replit.
Apache-2.0 ★ 1 -
vent-widgetgithub.com/CharlesTThe/vent-widgetupdated this year
MCP server that lets AI agents log friction to .vents/ markdown files in your repo. Open-source implementation of Lovable's vent-tool pattern.
MIT -
DarkLens Model Context Protocol (MCP) Server: Real-time dark pattern and compliance auditing for AI coding agents (Cursor, Windsurf, Claude Desktop, Lovable).
npm MIT -
NightMarqueeno update data
Art-directed website prompts delivered as slash commands in Claude Code, Claude Desktop and Cursor: hero sections, landing pages, SaaS, portfolio, e-commerce and 3D/WebGL scenes. Each build is registered as a real MCP prompt and written natively for the tool you are in (Lovable, Bolt, Cursor or Claude), with a live demo you can scroll before spending a token.
smithery -
Find the security holes your AI left behind. Zero-config scanner for apps built with Cursor, Claude Code, Lovable & Copilot: leaked keys, open Supabase/Firebase data, missing auth, SQL injection and more. Every finding comes with a fix prompt for your AI editor. CLI + MCP server
MIT ★ 2 -
privacypage-mcpno update data
Give your AI agent the power to generate privacy policies, terms of service, EULAs, cookie policies, and disclaimers — while it builds your app. Every app shipped from Cursor, Lovable, Bolt, or v0 eventually needs legal documents — the App Store and Play Store require a privacy policy, GDPR requires cookie disclosures, and users expect terms of service. This MCP server lets the agent that's building your app generate those documents in the same conversation, filled in from what the agent already knows about your app: its name, platform, the data it collects, and the SDKs it uses.
smithery -
briefkit-mcp-servergithub.com/mithun4elp/briefkit-mcp-serverupdated this year
BriefKit — Engineer-grade specs for AI-built SaaS. 14 files. $9. briefkit.online
MIT ★ 1 -
—
Apache-2.0 ★ 10 -
MCP server exposing Neural Draft's content/blog/social/booking/commerce APIs to AI coding tools (Claude Code, Cursor, Continue, etc.).
npm MIT -
vulk-mcp-servergithub.com/devjoaocastro/vulk-mcp-serverupdated this year
VULK MCP Server — Build full-stack web applications from any AI assistant
MIT -
Local, offline MCP server for jevify: find the AI calls in your code that are really decisions, then plan their migration to JEV in shadow mode.
npm Apache-2.0 -
Free MCP server, Cursor rule and Claude skill that help AI coding assistants avoid common security holes in vibe-coded apps (Supabase RLS, leaked keys). By SealMyApp.
MIT -
@axonscape/launchpad-mcpactive
Launchpad's MCP server: lets Claude Code, Cursor or any MCP client check an AI-built app is safe to launch, then deploy it on accounts you own.
npm MIT -
The go/no-go check for AI-built apps. Reads your repo on your machine, lists what will break in production, and exits 0 only when nothing serious is left.
npm MIT -
teamonlyactive
Deploy the internal tools you build with Claude Code or Cursor behind your company login, in one command. Database, files and secrets included. CLI, MCP server and SDK for TeamOnly.
npm SEE LICENSE IN LICENSE -
Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQL. Hosted version: Locksoup.
MIT ★ 50 -
Finds what a visitor, or another signed-in user, can read and change in a Supabase app by running its migrations offline, explains it in plain words, and tells your AI builder what to fix. CLI, GitHub Action and MCP server.
npm MIT -
Measure the AI slop on any website, then fix it. Scans a whole site, a local app or a project folder for generic copy, template design and unfinished details, and gives step-by-step fixes your own AI can apply. MCP server + CLI.
npm MIT