Web Search MCP Repositories

Search and retrieve flight information leveraging the Duffel API, particularly adept at managing complex travel plans with contextual memory of previous searches.

Control Chrome tabs, execute JavaScript, capture screenshots, and monitor network traffic. Enhance browser automation capabilities by integrating directly with Chrome's DevTools Protocol.

Connect to a SearXNG instance to perform search queries via the Model Context Protocol (MCP), facilitating integration with compatible AI clients.

Interact with Twitter to analyze sentiments and retrieve tweets from timelines, providing insights into public opinion and updates on trending topics.

Interact with YouTube data to search for videos, channels, and comments, and analyze performance metrics. Retrieve transcripts and generate summaries of video content.

Integrates with The Movie Database (TMDB) API to provide access to movie information, search capabilities, and personalized recommendations.

Provides a framework for concurrent web crawling tailored for large language model applications, allowing for the extraction and structuring of web content with customizable settings for depth and domain restrictions. Integrates seamlessly with the Model Context Protocol to facilitate web data integration into LLM workflows with effective error handling and batch processing capabilities.

Fetches auction listings from Ebay.com using simple prompts to discover various items, like comics or collectibles, by leveraging Ebay's REST API for real-time auction data.

Interact with web content through standardized tools to fetch and summarize information from any website.

Integrates with SearXNG to provide privacy-focused meta search capabilities, combining results from multiple search engines without tracking or profiling users. Supports various categories, languages, and filtering options, ensuring reliable and safe search experiences.

Integrates the SearXNG API to provide web search functionalities including retrieving general queries, news, and articles with advanced filtering options.

Explore and analyze websites implementing the llms.txt standard, validating and parsing llms.txt files for structured insights about compliant websites.

Interacts with YouTube content by retrieving video details, managing channels, and accessing transcripts through a standardized interface. Allows for video statistics, channel management, and playlist details.

Fetch web content in various formats like HTML, JSON, plain text, and Markdown. Retrieve and transform website data on demand with customizable headers.

A multi-platform intelligent dialogue service that supports text, voice, and image interactions. It can connect to various AI models and allows for custom enterprise AI applications through plugin extensions.

Provides seamless access to Google Cloud's Vertex AI Gemini models for coding assistance and general query answering, with enhanced query responses grounded in web search and direct knowledge.

Provides online and local search capabilities with support for multiple search engines including Brave Search, Metaso Search, and Bocha Search. Designed for integration with AI models like Cursor and Claude Desktop, enabling enhanced content retrieval.

Provides real-time web search capabilities and access to premium data sources, including news, financial markets, sports, entertainment, and weather information. Facilitates the development of AI agents leveraging diverse data models.

Integrates the Sonar API for live web searches, enabling conversations that leverage real-time web-wide research capabilities. Facilitates instant information retrieval directly from the web during interactions.

Search for npm packages using the `npm search` command to find relevant libraries and tools from the npm registry.

Fetch web page content using a headless browser, capable of executing JavaScript to handle dynamic web pages and modern web applications. Extracts the main content intelligently using a Readability algorithm and supports output in both HTML and Markdown formats.

Access the Metropolitan Museum of Art's collection through natural language queries to search for artworks and retrieve detailed information on various departments.

Perform accessibility audits on webpages and generate detailed reports and summaries that comply with WCAG standards. Integrate the findings into an AI-assisted workflow to fix accessibility issues efficiently.

Enables AI agents to scrape web content, search for specific text snippets, and perform structured information extraction from websites using natural language instructions. Utilizes LLMs for intelligent content retrieval and provides an API for interaction.

Integrate with the Sonar API to conduct real-time web searches through conversational interactions, enabling enhanced research capabilities with live data.

Fetch and explore web content autonomously by navigating through documentation and web pages to extract relevant information. It supports recursive exploration and filters navigation links for content-rich pages.

Connect AI models to real-time data and tools with features such as weather querying, Google search automation, camera control, and image generation. The server supports modular expansion and custom API integration for tailored functionalities.

Extract transcripts from YouTube videos by providing a video URL. The server supports multiple URL formats and returns the transcript text in a structured array format.

Access real-time earthquake data from the USGS API, enabling users to query earthquake information based on various parameters and retrieve details about specific events.

Scrapes data from popular social media platforms such as Xiaohongshu, Douyin, Kuaishou, Bilibili, and Weibo. Extracts videos, images, comments, likes, and shares using Playwright for efficient data collection.