Web & APIs MCP Servers

SEO for AI agents: crawl sites, audit pages, pull Search Console data, generate shareable reports.

Cloud scraping & crawling API for AI agents. Turn any URL into clean, LLM-ready markdown.

Search a curated RSS feed directory and fetch latest articles. EN/JA. Sign in to use favorites.

Website traffic, DR growth and payment rankings; manage website and keyword favorites via OAuth.

Publish a complete website to a live URL from your AI assistant: forms, bookings, content, chatbot

URL to clean markdown for LLMs: a polite, robots.txt-respecting web reader. Free, no API key

Superseded by io.github.f-tiger/hvac-btu-heat-klimaanlage — same server, same URL.

Build, edit, host, and publish websites from AI assistants. Setup: https://mcp.orivox.org/

Affiliate product search for AI agents. Merchant feeds, not web scraping. Works with any MCP client.

Read-only ArcadeOps discovery for developer docs, OAuth, OpenAPI and synthetic sandbox.

Paid web, news, company, product, and geographic search plus clean page reading for agents.

Scrapes Google News and returns the real publisher URLs, not redirect links.

Unified data server: stocks, crypto, news, weather, web scraping, FX rates in one MCP

SSRF-safe web intelligence: 4 outcomes, 43 paid x402 tools, 3 free tools and a URL preview.

A proof-of-concept implementation of a Model Context Protocol (MCP) server that runs in WebAssembly (WASM) within a web browser. This project demonstrates the integration of MCP tools and resources in a browser environment.

Self-hosted MCP server with SearXNG + Crawl4AI for fast search and reliable web scraping in Claude Code. 3x faster than native tools with 100% scraping reliability.

Browser automation for Claude via WebDriver and MCP. Support for Chrome/Firefox with stdio/HTTP transport.

MCPify is a NuGet package that dynamically loads OpenAPI/Swagger specifications at runtime and exposes each API operation as a tool in an MCP (Model Context Protocol) server.

Fetch any URL and get clean Markdown. Web scraping for AI agents.

Reference mcp server implementation of draft mcp oauth spec https://modelcontextprotocol.io/specification/draft/basic/authorization#2-3-authorization-server-discovery

Turn any OpenAPI/Swagger spec into an MCP server - every API operation becomes an agent tool.

MCP-based agentic AI system enabling LLMs to fetch and reason over real-time global weather data using standardized tool invocation. Built with MCP Server/Client, Llama 3, and external APIs to deliver low-latency, hallucination-free weather intelligence through protocol-driven workflows.

Audit websites for accessibility, performance, SEO, design, and mobile. 47 WCAG checks.

Fetch, parse, screenshot and browse pages via MCP without a real browser -- no JS execution.