Extract visible text, HTML, or linked URLs from the current page or a specific element for scraping, crawling, and resource inspection.
MIT
510,634 tools. Updated 2026-09-04 09:24
"A tool for extracting text from a webpage after crawling it" matching MCP tools:
- Retrieve visible text, HTML, or discovered URLs from a page or element to access actual content for crawling, link discovery, or scraping.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
- Extract new data from a completed crawl without re-crawling pages. Submit a new prompt and receive a jobId to track progress, paying only for AI tokens.MIT
- Summarize long documents into a concise prose summary and key points, each with cited evidence. Use after extracting text or URL content to quickly grasp key takeaways.MIT
- Diff two webpage states or PNG captures to get before, after, and mismatch metrics for QA and visual regression testing.MIT
Matching MCP Servers
- AlicenseAqualityDmaintenanceMCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.11MIT
- FlicenseNot gradedqualityCmaintenanceLocal MCP server for A-share stock trading via Tonghuashun, offering account/position queries, buy/sell/cancel orders with risk controls and forced user confirmation; currently simulated with a reserved interface for real broker channels.
Matching MCP Connectors
An MCP connector for Adobe After Effects. Real, editable layers and keyframes, not scripts.
Manage your Canvas coursework with quick access to courses, assignments, and grades. Track upcomin…
- Extract and classify all links on a page into internal vs external, with anchor text, nofollow attributes, and counts. Use for link audits, internal linking reviews, and competitor link building analysis.MIT
- Take a rendered screenshot of a webpage after JavaScript execution. Use for visual audits, above-the-fold analysis, competitor comparison, UX review, or documenting page state.MIT
- Ingest your company's website content into Mira knowledge base by crawling sitemap and same-origin links, extracting, chunking, and embedding readable text. Monitor crawl progress via status reads.MIT
- Fetch a webpage and extract its main text, stripping navigation, headers, and scripts for clean reading. Use this to access full page content after a search.MIT
- Initiates an asynchronous crawl of a website, extracting content from multiple pages. Use for comprehensive site coverage; monitor progress with returned operation ID.MIT
- Retrieve original tool result content from a flattened session backup by specifying the tool use ID and session ID from the conversation.MIT
- Send a prompt to a local Ollama model for immediate private answers. Use it for summarising text, drafting boilerplate, or extracting fields without sending data off-machine.MIT
- Ingest a document file locally by extracting its text and storing it as a recallable entity in memory. Supports plaintext, markdown, and structured text; DOCX and PDF require a specific build.MIT
- Summarize a short non-video webpage into Markdown. Accepts optional instructions and can bypass cache to refresh the summary.MIT
- Extract readable text content from a webpage URL by stripping scripts and navigation elements. Returns up to 2000 characters of meaningful text.MIT
- Fetch a URL and get a JSON list of all links classified as internal, external, or other, with anchor text. Ideal for crawling a site for migration or building a sitemap.MIT
- Extract plain text from a webpage, prioritizing article content for easy reading. Provide a tab ID to retrieve text without HTML formatting.Apache 2.0
- Classify a local PDF as text-based, scanned, image-based, or mixed, returning confidence and exact pages needing OCR, without extracting text.MIT
- Fetch full webpage content as clean markdown. Use after search results when highlights are insufficient, or to extract complete text and metadata from known URLs. Batch multiple URLs in one call.MIT