MCP servers · Web search, scraping & browser
50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.
- Kloakt ★ 1
Cloaked headless browser for AI agents — stealth TLS, smart extraction, SPA fallback - Tap ★ 17
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay. - BrowserTap MCP ★ 2
MCP server that drives the real Chrome you already use, through an extension and CDP. - Syftly
Ranks the best AI tool or API per task: transcription, TTS, web search, scraping and OCR. - SourceWeave Web Search ★ 2
Fully local MCP server and CLI for web research - io.github.MastadoonPrime/sylex-search ★ 4
Universal search engine for AI agents. Discover products, services, and businesses via MCP. - WaveXisMCP ★ 1
220 browser automation tools for Chrome, Edge, and Firefox via CDP + BiDi. 100% Python. - kite-lite
Fetch, parse, screenshot and browse pages via MCP without a real browser -- no JS execution. - io.github.MetaLift-AI/metalift
Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools - Obscura MCP ★ 2
MCP server adapter for Obscura Rust headless browser — web scraping with anti-detection. - Data Enrichment & Web Scraper API
Enrich IPs, emails, domains, companies. Scrape SEC, news, jobs, Crunchbase. Bitcoin pay-per-use. - acrawl ★ 12
Autonomous web crawler. 17 browser tools + goal-driven run_goal agent. Single binary, stealth. - io.github.ModelPiper/toolpiper ★ 2
On-device MCP tools for macOS: local AI, speech, vision, browser automation, system control. - io.github.ObscuritySRL/bun-uia ★ 19
Playwright for the Windows desktop, from Bun — drive native GUIs via UI Automation + MCP. - WebsiteIQ
Robots-aware website audits, pre-crawl quotes, and structured evidence for people and agents. - io.github.Perufitlife/deep-research-mcp-server
Web search, clean page reading & one-call research dossiers for AI agents. No API key. - io.github.PramodDutta/browserbash ★ 1
Plain-English browser tests for AI agents: real Chrome, deterministic verdicts. Free, no API keys. - QualityMax QA MCP ★ 2
Local QA MCP: scan URLs, inspect pages, generate Playwright repros, and run tests. - io.github.RapierCraft/perplexity-comet-mcp ★ 48
Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management - PageMap ★ 36
Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy - SocialCrawl
One API for 65 platforms and 572 endpoints: social, commerce, retail, jobs, finance, web scraping. - MCP Retrieval ★ 12
Local Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown. - Ikenga iyke (control bridge)
Drive a running Ikenga desktop app from MCP clients — DOM, click, type, navigate, screenshot. - io.github.ScrapeGraphAI/scrapegraph-mcp ★ 110
AI-powered web scraping and data extraction capabilities through ScrapeGraph API - Tavily MCP Server
MCP server for advanced web search using Tavily API. - shaft-mcp ★ 409
SHAFT browser automation, capture, and offline deterministic failure diagnosis - io.github.Shreyas-Profile/browser-mcp
Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot. - SilbercueSwift — iOS MCP Server ★ 8
iOS MCP server: 49 tools free (58 with Pro), xcresult parsing, WDA UI automation, fast screenshots. - Skyvern ★ 22,993
AI-powered browser automation — navigate, click, fill forms, and extract data from any website. - io.github.Slowper/anylens
Turn videos, PDFs, screenshots, and articles into anchored, cached understanding for agents. - Payx Tavily Search
FastMCP server for Tavily search API with web search and content extraction - io.github.TN0123/one-shot-ui ★ 4
Deterministic UI extraction and screenshot diffing for AI coding agents. - io.github.TickTockBent/charlotte ★ 179
Renders web pages into structured, agent-readable representations using headless Chromium. - io.github.Tlalvarez/auxiliar-mcp
Web access for AI agents — search/scrape/extract/crawl via the auxiliar.ai gateway. - web-retrieval-mcp ★ 1
MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform. - Vibe MCP — Real Chrome, Remotely ★ 3
Drive your real, logged-in Chrome from any MCP client — even from a remote machine, no inbound port. - io.github.Xavierfok/singapore-proxy-mcp
Browse the web and run Google search through real Singapore mobile carrier IPs. - Google Search Console ★ 8
Google Search Console: SEO audits, performance queries, URL inspection, indexing checks. - io.github.achiya-automation/safari-mcp ★ 186
Native Safari browser automation for AI agents — 98 tools, zero Chrome overhead. - io.github.adelpro/quran-search-engine-mcp ★ 6
Quran Search Engine MCP for AI tools. Provides Quran search, Arabic normalization, and highlighting. - AI Process Manager (AIPM) ★ 1
Structured Windows state for AI agents: processes, windows, UI trees. No screenshots. - io.github.aicrafted/searxng-mcp ★ 9
MCP server for SearXNG aggregator — web search across multiple engines via Model Context Protocol - Data Quality Gate - deterministic post-scrape cleaner + verdict
Post-scrape data cleaner, no LLM: repairs mojibake, HTML, invisible chars. Plus a verdict. - io.github.aimnis/search
Collaborative, cache-first web search for agents — cited answers from a shared live-web pool. - World Resolver
Resolve real-world capability gaps: validate native MCPs, search the web, and record unmet demand. - WebReaper ★ 147
AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed. - Frontend Design Loop MCP ★ 1
Design-first MCP for coding agents that improves websites with screenshot-grounded iteration. - nodriver — undetected browser automation ★ 4
Undetected anti-bot Chrome automation. 65 tools, parallel isolated browsers. - io.github.annibale-x/webshift ★ 7
Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents. - io.github.antonkarliner/truepane ★ 2
Local MCP server generating complete App Store & Google Play screenshot sets.