Web Search MCP Repositories

Enables advanced web scraping and content extraction, supporting JavaScript rendering and batch processing for deep research. It includes features for automatic retries and efficient data integration while monitoring credit usage and handling rate limits.

Enables web search using the DuckDuckGo search engine, providing structured search results along with metadata and smart content classification.

Connects AI models to the web for real-time information retrieval, webpage content extraction, and research session tracking, along with the ability to capture screenshots.

Extracts and queries data from various financial websites while allowing seamless switching between sources in case of outages. Utilizes browser automation for accurate data retrieval without needing manual logins or complex request handling.

Connect to Bluesky and interact with the ATProtocol using natural language to fetch, analyze, and post content seamlessly. Provides access to various Bluesky API endpoints directly within LLM applications.

Provides access to high-quality world knowledge from billions of web pages and various ecological content sources through a powerful search engine interface. Supports natural language semantic search, offering rich, structured results and vertical domain cards for enhanced information retrieval across multiple domains.

Retrieve and process web content by converting HTML to markdown, enabling easier extraction of information in manageable chunks. Supports starting extraction from a specified character index for better navigation of web content.

Access the Gallica digital library to search for documents, images, maps, and other resources, and generate structured research reports that include organized bibliographies and relevant visual content.

Interact with OpenDeepSearch's search functionalities through a standardized interface, enabling LLM applications to leverage advanced web search capabilities. Integrates seamlessly with MCP-compatible clients for enhanced search integration.

Access and render content from Baidu Baike, providing detailed discussion data for specific entries and generating readable analyses that highlight key topics and trends. Integrate rich insights from Baidu Baike seamlessly into applications.

This utility retrieves digital asset records from the Origin Forge platform via its API, similar to how a software system presents hyperlinks based on a user's web query. It captures and saves the associated vector graphics (SVG) and descriptive data structures (JSON metadata). The tool enhances the visualization experience of these unique digital items by offering functions to access specific item characteristics and visual components.

Run accessibility tests on web applications to identify compliance issues and enhance digital accessibility. Utilize axe-core and Puppeteer to generate detailed violation reports with information about impact levels and affected elements.

Retrieve and process web content from URLs, converting HTML to markdown for easier information extraction. Enables chunked content retrieval for efficient parsing by LLMs.

Seamlessly access Bilibili's API, enabling advanced searching and data retrieval operations for users, videos, live streams, and articles, as well as fetching video comments (danmaku). Offers functionalities for general searches and precise filtering of results across various content types.

Retrieve MCP Servers through semantic search capabilities, allowing users to find relevant servers efficiently based on queries.

Provides cryptocurrency sentiment analysis by aggregating social media and news data to assess market mood and detect trends. It offers insights into sentiment balance, social media mentions, and trending discussions surrounding various cryptocurrencies.

Enables web search, scraping, and content extraction from various websites using multiple search engines and scrapers. It supports local browser searches and integrates with tools like SearXNG, DuckDuckGo, and Bing for enhanced data retrieval.

Perform web searches and retrieve information using the Tavily API, returning results in text format along with AI responses, URIs, and titles.

Provides advanced web browsing capabilities for AI applications, enabling interaction with web content and retrieval of information from online sources.

Facilitates job searching on LinkedIn by utilizing the unofficial LinkedIn API for credential management and job scraping. Matches job opportunities using JobSpy for enhanced search capabilities.

Automates article generation and posting on Zhihu using large language models. Integrates with MCP clients to facilitate content creation workflows through automated browser interactions and cookie management.

Retrieves detailed Weibo user information, feeds, and conducts user searches. Facilitates the analysis and scraping of Weibo data for integration into various applications.

Interact with LinkedIn to scrape profiles, analyze companies, and search for job listings. Provides insights and recommendations based on LinkedIn data.

Gemini Pro Chat provides a minimal web interface for interacting with the Gemini Pro AI model. Users can deploy their own instances and customize the integration using an API key for secure and seamless operation.

Interact with the Farcaster Network to fetch casts, search channels, and analyze content related to users and channels. Retrieve user-specific casts through FID or username, as well as casts from specific channels.

Extract plain text from any web page URL and convert it to clean, well-formatted Markdown output. Provides robust error handling and is optimized for AI consumption through seamless integration with MCP clients.

Leverage the GitHub search API to retrieve relevant data from GitHub repositories, enabling advanced search capabilities for applications. Efficiently integrate and utilize data from various GitHub resources.

Extract insights from YouTube videos, analyze transcripts, and retrieve metadata and channel information. Enable keyword-based video discovery to support content strategy development.

Facilitates efficient search and exploration of research papers from arXiv.org, enabling users to access detailed metadata, conduct keyword and author-based searches, and generate prompts for summarization and comparison. Provides updates on trending topics across various research categories.

Integrates Google Custom Search to retrieve search results and perform detailed analysis of webpage content. Supports multiple output formats and provides features for categorization, summarization, and optimized responses.