Search the web, news, or images and scrape result URLs to extract markdown, HTML, links, or screenshots for research and data gathering.
Server Side Public , v 1
534,466 tools. Updated 2026-09-08 14:44
"Web scraping tool for extracting content from SearXNG search results" matching MCP tools:
- Fetch any web page and receive AI-parsed structured JSON instead of raw HTML, extracting product details, articles, or listing fields without writing custom parsing code.MIT
- Search Google Jobs to get normalized job results from public web responses, enabling structured recruitment and job search workflows.MIT
- Get search query suggestions for partial keywords. Use it to discover relevant terms before running a full search.MIT
- Perform AI-powered web searches to extract structured data from search results for research, competitive analysis, and multi-source information gathering.MIT
- Retrieve parsed Google Search results as structured JSON. Get organic results, ads, knowledge panels, and pagination for any query without scraping HTML.MIT
Matching MCP Servers
- AlicenseAqualityBmaintenanceA Model Context Protocol server that provides real-time web search capabilities to AI assistants through pluggable search providers, currently integrated with the Brave Search API.516MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP Server that provides access to Google's Cloud Tool Results API, enabling applications to programmatically interact with test results from Firebase Test Lab and mobile app testing through natural language.-
Matching MCP Connectors
Google Web Search: Google Web Search API. Search the world’s information, including webpages.
Generic URL crawl + HTML extraction — fallback for sites without dedicated MCPs.
- Get a list of enabled search engines and categories from your SearXNG instance. Use it to choose specific filters before running a search.MIT
- Search the web and get clean, structured results with titles and snippets, bypassing anti-bot restrictions.MIT
- Convert webpages into clean, formatted markdown for extracting content from documentation, articles, and web pages. Fetches any webpage and transforms HTML content into readable markdown format.MIT
- Search the web via 200+ engines with privacy, getting aggregated results, answers, suggestions, and infoboxes. Filter by category, language, or time range.MIT
- Search the web for a query and retrieve up to 10 SERP results including title, URL, snippet, engine, and score. Use snippets to answer simple questions; call the scrape tool separately for full page content.-
- Search BPS statistics content (publications, tables, press releases, infographics, microdata, glossary, classifications) via AllStats Search Engine with filters for region, year, and content type.MIT
- Search Apify and Crawlee docs via full-text queries to find relevant pages on platform features, SDKs, CLI, REST API, and web scraping libraries.MIT
- Search the web for a query, then retrieve complete page content from the top results to provide detailed, in-depth information for comprehensive research.MIT
- Search the web by query, optionally returning markdown content, with country targeting and JavaScript rendering for dynamic pages.MIT
- Extract the full content from a specific web page by providing its URL, without performing a search.MIT
- Extract clean content from a public URL, returning Markdown, text, metadata, links, JSON-LD schema, and sections for scraping, RAG ingestion, or content analysis.MIT
- Perform web searches using SearXNG API to gather information, find news and articles, or explore diverse online sources for general queries and recent events.MIT
- Convert any public URL to Markdown. Extract readable content from web pages, articles, and documentation as structured Markdown.MIT
- Perform web searches to gather real-time information, news, and detailed content analysis with customizable parameters for results, domains, and timeframes.MIT
- Extract and process web content from URLs for data collection, content analysis, and research tasks, supporting multiple formats and extraction depths.MIT