convert_to_markdown
Convert to Markdown
Convert a webpage into a downloadable Markdown document, with optional chunks for indexing, keyword-matched passages, page metadata, headings, links, and images.
Ask your agent in plain language. Each of these maps to a real tool on the server.
convert_to_markdown
Convert a webpage into a downloadable Markdown document, with optional chunks for indexing, keyword-matched passages, page metadata, headings, links, and images.
scrape_html
Fetch the raw HTML content of any public webpage. Handles anti-bot protections, JavaScript rendering, and complex site structures. Use this to retrieve full page HTML for parsing, content analysis, or data extraction workflows.
get_oembed
Get an oEmbed representation of a URL, including embeddable HTML, dimensions, and provider metadata. Uses a native provider embed when available and a hosted preview card otherwise.
unfurl_url
Extract Open Graph metadata, Twitter Cards, and HTML meta tags from any URL. Returns a **hybridGraph** that merges OpenGraph tags, Twitter Card data, and inferred metadata from page content for the most complete result. Use this to generate link previews, validate social sharing metadata, or gather structured information about a webpage.
query_page
Ask a question about any webpage and get an AI-generated answer based on the page's content. Supports multiple AI model sizes and optional structured response formatting. Use this to extract specific information, summarize content, or answer questions about a page without manually scraping and parsing it.
extract_content
Extract specific HTML elements from a webpage in a structured format optimized for AI/LLM pipelines. Returns individual tagged elements with their text content and position, plus a concatenated text output ready for processing. Use this for content analysis, text extraction, or preparing webpage content for AI workflows.
capture_screenshot
Capture a screenshot of any webpage. Returns a URL to the screenshot image. Supports multiple viewport sizes, full-page capture, element-specific capture via CSS selectors, and image format/quality settings. Use this for visual previews, monitoring, or archiving webpage appearances.
Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.
{"mcpServers": {"metorial": {"url": "<your-magic-mcp-url>"}}}
claude mcp add --transport http metorial <your-magic-mcp-url>
codex mcp add metorial --url <your-magic-mcp-url>codex mcp login metorial
One governed layer for every app your agents reach, not a separate connector per tool.
Extract Open Graph metadata, Twitter Cards, and HTML meta tags from URLs. Scrape HTML, capture downloadable screenshots, extract page content, ask AI-powered questions, convert pages into downloadable Markdown, and retrieve embeddable preview cards. Supports caching, JavaScript rendering, proxies, content chunks, and language preferences.
Common questions about connecting Opengraphio to AI agents with Metorial.