Explore server capabilities, recorded tools, available client configurations and practical setup considerations. Browse servers by category, or jump to remote servers and official vendor servers.
Servers can appear in several categories when their tools support several tasks. Category counts include these overlaps; the directory total counts each server once.
1206 servers
2524 servers
11811 servers
1975 servers
617 servers
3760 servers
2503 servers
2250 servers
2026 servers
3592 servers
1484 servers
1773 servers
451 servers
1244 servers
77 servers
115 servers
1191 servers
143 servers
370 servers
1745 servers
896 servers
2415 servers
383 servers
522 servers
1352 servers
160 servers
320 servers
661 servers
253 servers
1374 servers
865 servers
1537 servers
1041 servers
940 servers
499 servers
627 servers
339 servers
464 servers
234 servers
214 servers
379 servers
435 servers
829 servers
931 servers
151 servers
3626 servers
245 servers
135 servers
998 servers
676 servers
1478 servers
395 servers
152 servers
429 servers
423 servers
386 servers
344 servers
1286 servers
234 servers
326 servers
60 servers
699 servers
341 servers
492 servers
300 servers
322 servers
283 servers
556 servers
447 servers
208 servers
72 servers
249 servers
176 servers
336 servers
60 servers
32 servers
25 servers
31 servers
34 servers
194 servers
78 servers
31 servers
69 servers
159 servers
66 servers
31054 servers
Traversable webring directory for the agentic web: agents, MCP servers, and agent-ready websites.
Search, extract, answer, research and browse the web through one interface, across many providers
A remote WebRTC chat server with secure temporary rooms and MCP support for background agents
WebRtcPerf is an open-source tool designed for testing WebRTC services with multiple concurrent client connections, measuring the most important RTC
Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.
MCP server for web content scanning and analysis
Audit any live URL: 85 SEO, AI-search, security, leaked-key and speed checks, with fixes to verify.
Short project answers for coding agents: grouped search, one symbol per read, the project's scripts.
To install Web Scout for Claude Desktop automatically via Smithery:
MCP server for web search and content extraction with multiple URL support and memory optimizations
A FastAPI application that performs web searches using DuckDuckGo and generates AI-powered summaries using Google's Gemini AI.
Fetch any URL and get clean Markdown. Web scraping for AI agents.
A collection of production-ready Model Context Protocol servers for Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.
Fetch, crawl, and browse protected pages with anti-bot handling - renders in a real browser and
MCP server for web scraping and converting web pages to Markdown with Playwright support
Website to clean Markdown or JSON for AI and RAG: read pages, crawl sites, extract described fields.
Certified by MCPReview https://mcpreview.com/mcp-servers/saishridhar/webscraper
Extract clean markdown from any URL. Strips nav/ads/scripts, returns structured content. Built for RAG pipelines and AI research agents. Pay-per-call via x402 (USDC on Base L2) -- no API key, no…
Web scraping for AI agents: scrape, search, crawl, map any website to markdown + JSON. No browser.
Interact with WebScraping.AI for web data extraction and scraping.
# 🚀 **We’ve just launched our new MCP server!** If you're building or using AI agents, you can now plug our web scraping API directly into your
Generic URL crawl + HTML extraction — fallback for sites without dedicated MCPs.
Or with Docker Compose: ```sh docker compose --profile service up -d ```
A Model Context Protocol (MCP) server that enables free web searching using Google search results, with no API keys required.
Live web search and clean-markdown page fetch over the Keenable web index.
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
Search the web and fetch a page's readable text.
Multi-engine web search, fetch, browser control. 11 tools, keyless lanes.
Captcha-avoiding web, news, image and video search plus page fetching over free sources
Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.
Web search API for AI agents. Structured results with title, URL, snippet. Current news, docs, research. Up to 10 results per query. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup…
Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.
Live web search, image search, topic filters and full-text fetch over our own crawled index.
Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
Search the web and read pages from your AI assistant, with results it can cite.
A comprehensive Model Context Protocol (MCP) server built with FastMCP that provides LLMs with real-time, high-fidelity access to the web. This server aggregates multiple search engines, social…
A TypeScript MCP (Model Context Protocol) server that provides comprehensive web search capabilities using direct connections (no API keys required) with multiple tools for different use cases.
Parameters: - query (required) — The search query - count (optional, default 5, max 10) — Number of results
A Model Context Protocol (MCP) server that provides web search functionality by scraping Google, DuckDuckGo, and Bing search results through a
This project demonstrates how to create a web search tool using the Tavily API and integrate it with MCP (Model Context Protocol) for seamless interaction with AI Systems. This allows you to provide…
A Model Context Protocol (MCP) server implementation that provides real-time web search capabilities through a simple API
A Model Context Protocol (MCP) server that provides a web search tool using the Tavily API. This server enables AI models to search the internet and retrieve up-to-date information.
Zero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetch
Search the web and the news from an agent, with page text in the results when you ask for it.
A powerful web search and content extraction tool built with Python, leveraging the Firecrawl API for advanced web scraping, searching, and content analysis capabilities.
A powerful web search and content extraction tool built with Python, leveraging the Firecrawl API for advanced web scraping, searching, and content
Manage your Webshare proxies, usage, plans and billing. Sign in with OAuth, no API key.
Search the web and extract article text for LLMs.
Drive a real browser with shell-like text commands (cd/ls/cat/click/type), using far fewer tokens.
Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.
Read orders, shipments and tracking events; create orders and rate quotes in Webshipper.
Fast, low-token web reader and focused crawler. Returns ranked passages, not whole pages.
Cuvo Health published site content and live discovery-call booking tools for AI agents.
Download website to a local directory (including all css, images, js, etc.)
Finds public VAT and company registration identifiers from website domains.
Reverse-engineer live pages into structured design tokens and docs your AI coding agent can use — colors, typography, spacing, components, layout, and responsive behavior.
An MCP server for website-auditor.io — AI-visibility (GEO) and site-audit tools you can call from any MCP client (Claude Desktop, Claude Code, Cursor, Codex, and other agents).
SEO, broken links, Lighthouse, sitemaps, Open Graph tags and SSL expiry for any list of URLs.
Track page and price changes over time: diffs, history, and alerts through simple tracking
Monitor public pages and JSON endpoints after agents disconnect, with polling and webhooks.