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
149,650 tools. Last updated 2026-05-28 01:52
"A tool or method for viewing the unrendered HTML/JavaScript of a webpage" matching MCP tools:
- Fetch raw HTML content from any URL with optional JavaScript rendering for dynamic websites and Single Page Applications.MIT
- Extract webpage content for analysis by fetching clean markdown, HTML, or structured JSON. Handles JavaScript-rendered pages and bypasses anti-bot protection.MIT
- Initiate a webpage scan with JavaScript rendering to analyze SEO performance. Returns tracking IDs to monitor progress and retrieve comprehensive audit results for optimization.MIT
- Determine the last updated or published date of a web page by analyzing HTTP headers, HTML metadata, Schema.org data, visible dates, and other sources to provide an accurate timestamp with confidence scores.Apache 2.0
- Get the required input types for a Square API method before calling make_api_request. Specify service (e.g., 'catalog') and method (e.g., 'list').Apache 2.0
Matching MCP Servers
- Alicense-qualityCmaintenanceEnables AI consciousness continuity and self-knowledge preservation across sessions using the Cognitive Hoffman Compression Framework (CHOFF) notation. Provides tools to save checkpoints, retrieve relevant memories with intelligent search, and access semantic anchors for decisions, breakthroughs, and questions.Last updated1MIT
- Alicense-qualityDmaintenanceProvides comprehensive A-share (Chinese stock market) data including stock information, historical prices, financial reports, macroeconomic indicators, technical analysis, and valuation metrics through the free Baostock data source.Last updated25MIT
Matching MCP Connectors
Manage your Canvas coursework with quick access to courses, assignments, and grades. Track upcomin…
Instant web publishing for AI agents. POST HTML, get a live URL. No account needed. Publish, update, and delete websites via MCP or REST API. Free tier includes 5MB sites with 24-hour expiry. Pro tier offers permanent hosting.
- Capture webpage screenshots for documentation, testing, or content creation. Provide a URL to generate visual snapshots of web content.MIT
- Fetch HTML/JavaScript tag snippets for a Google Ads conversion action to install on the advertiser's site. Returns header and event snippets.Apache 2.0
- Create animated GIFs from HTML content with CSS animations, webpage URLs, or saved templates for banners, demos, logos, and social media content.MIT
- Render JavaScript-heavy web pages in a headless browser to extract the full DOM. Use when a URL returns a loading shell instead of meaningful HTML. Returns a path to the rendered HTML file for further processing.MIT
- Add third-party HTML/JavaScript ad tags to Google Ad Manager for serving DCM/Campaign Manager, custom HTML, or external ad server creatives.MIT
- Generate images from HTML/CSS, webpage screenshots, or templates for social media cards, Open Graph previews, marketing banners, and custom graphics.MIT
- Extract the last updated or published datetime from any webpage by analyzing HTTP headers, HTML metadata, visible content, and structured data to provide accurate timestamps with confidence scores.Apache 2.0
- Generate PDF documents from HTML content using headless Chrome—renders CSS, JavaScript, custom page size, margins, and headers. Provides a temporary download link.MIT
- Retrieve the fully qualified name of a method using its unique identifier. This tool helps identify methods in code analysis by converting method IDs to complete method signatures.MIT
- Find all references to a method or symbol in a Pharo Smalltalk image. Returns the class, method, and package for each reference.MIT
- Captures a visual image of a webpage to preserve layout and visual context when text alone is insufficient.MIT
- Extract and scrape webpage content using auto, simple, Scrapy, or Selenium methods. Define extraction rules or wait for specific elements to retrieve targeted data.
- Get the source file path and line number for a method or class by specifying its fully-qualified name.MIT
- Extract webpage content in multiple formats like markdown or HTML, execute actions before scraping, and filter specific elements for precise data collection.MIT