"Understanding the term 'throw' in web contexts" matching MCP servers:

A minimal MCP server that exposes Gemini's web and multimodal understanding (video, audio, document, image) through five dedicated tools.

An MCP server that analyzes local or remote GitHub repositories, providing intelligent code context and structure to AI coding assistants.

Persistent memory and pattern learning for AI coding assistants via MCP.

An MCP server that uses Google's Gemini API to analyze videos and convert them to text descriptions that Claude Code can understand and act upon.

An OAuth-secured remote MCP server (22 tools) that lets Claude, ChatGPT, and Codex search All-In Summit attendee profiles, explore the live agenda, check sessions and meetings, detect scheduling conflicts, and export a calendar. Account-changing actions are only prepared for review, with the user confirming each request in the browser before any event API call is made.

MCP server for controlling satellite ground station operations in the Trench simulation, including pass management, downlink control, and antenna pointing.

MCP server that lets AI editors execute JavaScript, read console output, and simulate clicks/input on static web pages. Supports multiple browser pages and can be deployed remotely via HTTP transport.

Enables live website health checks including TLS, HTTPS, and security headers, returning an A-F grade with specific fixes.

MCP server for multi-engine web search and web page fetching, supporting parallel search, content extraction, and optional LLM-powered search summarization and deep search.

Aggregates multiple MCP services into a single unified interface with self-configuration capabilities, enabling dynamic addition and removal of tools via conversation.

Enables web search via DuckDuckGo and web content fetching through the Model Context Protocol, allowing AI assistants to search and retrieve web page content.

Enables AI assistants to automate web interactions such as navigating pages, clicking elements, filling forms, querying the DOM, evaluating JavaScript, and inspecting network/console logs — all from a Termux terminal without Chromium, root, or proot.

Enables fetching, crawling, and browsing anti-bot protected web pages with real browser rendering, returning clean JSON or markdown, and solving captchas.

Provides a free web search tool to MCP clients by connecting to a self-hosted SearXNG metasearch instance, enabling users to search the web with customizable parameters like categories and time range.

Connect AI assistants to your Gramps Web family tree. Search and edit genealogy records, explore ancestors, descendants, relationships and timelines, and read document scans with vision-capable models. Includes guided research workflows, source citations, read-only mode, and privacy-aware media previews. Install with Docker or a Claude Desktop bundle.

Enables live-web research by providing stateless browsing, link extraction, and page search capabilities via Playwright, allowing agents to fetch and analyze web content without session management.

MCP server that fetches web pages and uses local Qwen models to answer questions about their content, with site-scoped search and map-reduce chunking for long pages.

MCP server for querying Google Gemini Web from Claude Code and other MCP clients, using cookie-based authentication. Enables creating, continuing, listing, viewing, and deleting Gemini chat conversations with model and thinking mode control.

Enables AI agents to extract clean, structured web content (articles, tables, links, visual layouts) optimized for LLM token efficiency, with fast response times and optional JavaScript support.

Provides an LLM client with self-hosted web scraping capabilities including scraping, crawling, mapping, searching, structured data extraction, browser interaction, and deep research, without reliance on paid proxy or CAPTCHA services.