MCP Server Directory

Debug PWAs in your real browser via MCP: service-worker, cache, installability & framework state.

Public discovery, scoped creator work, original-only recovery; checkout stays in owner's browser.

Native macOS browser exposing an MCP server so AI agents can drive a real WKWebView.

xpay Competitive Intel io.github.xpaysh/competitive-intel

40+ competitive intel tools. Brand.dev, Coresignal, Keywords Everywhere, Exa, Firecrawl.

Generate covers, Mermaid diagrams, cards, and terminal screenshots/images for AI workflows.

KATATAN E2E testing agent set — Playwright + KATATAN MCP integration

Autonomous web crawler. 17 browser tools + goal-driven run_goal agent. Single binary, stealth.

WhatsApp MCP via web.js or browserless Baileys: messages, media, chats, groups and contacts

Local-first MCP server for AI visibility, GEO/AEO, llms.txt, and AI crawler readiness audits.

Screenshot, PDF, and markdown extraction from any URL via Claude Desktop and Claude Code.

Crawlbase io.github.pipeworx-io/crawlbase

Crawlbase MCP — wraps the Crawlbase Crawling API (crawlbase.com, formerly ProxyCrawl). One…

Firecrawl io.github.pipeworx-io/firecrawl

Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web scraping / crawling / search…

URL to screenshot with metadata. Python MCP server. Claude Vision optimized.

Drive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP.

ShotAPI MCP Server io.github.smallhandsome/shotapi-mcp-server

Screenshot and HTML render MCP server for AI agents

Send and receive on-chain private messages via SealedMail on Sui. No browser wallet needed.

ToolPipe MCP Server io.github.COSAI-Labs/toolpipe

45+ dev tools via MCP: JSON, QR, hash, DNS, code review, fake data, screenshots, and more.

fastCRW io.github.us/fastcrw

Scrape, crawl, map & search the web. Open-source, self-hostable Rust crawler & search for AI agents.

Compare-first local MCP sidecar for browser AI workflows.

Shots run.shots/shots

Create App Store screenshots, icons, ASO copy, localization, and revisions via hosted MCP.

Convert HTML or URLs to PDF documents powered by Playwright

Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.

Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy

PageCrawl io.github.pagecrawl/pagecrawl-mcp

Monitor web pages for changes with AI-powered change detection, diffs, and alerts.