202 services carry this tag in their source record. Tags come from the provider, not from us — a tag is a claim about what the service does, not proof that it does it well.
Loudness-normalize any audio/video URL to a target LUFS with ffmpeg's loudnorm (EBU R128) and return MP3 - consistent levels for podcasts, clips, and TTS output. Body: {"url":"https://…/audio.wav","targetLufs":-16?}.
Web search that returns READY-TO-USE grounding text, not links: for one query you get the passages an independent search index extracted from the pages it ranked, flattened into chunks with their source URL and title and...
Crawl a website from a starting URL and return each page as clean markdown: breadth-first over internal links, bounded by page count and depth, honouring robots.txt, with per-page title, status, depth and outbound links....
Pull structured data out of any web page deterministically - articles to clean text, tables to JSON rows, specific elements via CSS selector - without writing regex against raw HTML. Structured scrape skill pack: one x40...
Use when an agent needs base block number. Returns Fetch the current Base mainnet block number from redundant public RPCs and return structured JSON with source and freshness metadata. $0.002.
Retrieve the readable text of up to 10 web pages by URL, with optional query-focused highlights. Pages are served from a crawl cache when the page is fresh enough and live-crawls otherwise, so this answers for pages a pl...
Live image search: ranked image results (title, source page, image URL, thumbnail URL, dimensions) from an independent search index as clean JSON. Strict safe-search is on by default.
Live video search: ranked video results (title, video page URL, description, duration, creator, publisher, thumbnail, age) from an independent search index as clean JSON. Completes the web/news/images search family. Same...
Look up one X (Twitter) account by username: id, display name, bio, account creation date, verification status and type, location, link, protected flag, and public metrics (followers, following, tweet count, listed count...
Read one known URL: the main article content as clean markdown with title, byline, excerpt and word count, boilerplate removed. Use it when an agent already has a URL and needs the text; for JavaScript-rendered pages tha...
Fetch a PDF from a URL and extract its text content. Returns page count, document info, and the full text (up to 20MB PDFs).
Extract text from a PNG or JPEG image - full text, overall confidence and per-line bounding boxes - from a URL or base64 payload, Tesseract on-device (no upstream API). Default English; other ISO 639-2 languages on reque...
Retrieve deterministic evidence from a public HTTPS page
Read ONE JavaScript-heavy page (single-page apps, dashboards, content loaded after page load) in a real Chromium browser and get the rendered text with title, description, word_count and optional links. Slower and pricie...
Web research in one call: search, then read the top 8 pages in full (clean markdown, each with a prompt-injection check) and pull the key passages that answer the query, with their sources. For agents that need evidence...
Web search for AI agents: search the web for any query and get ranked results (title, URL, snippet) plus the full text of the top 1-3 pages, each read in a real browser, as clean JSON. Filter by date, site or news. Find...
Neural (embedding-based) web search over a curated web index, which finds pages by meaning rather than keyword overlap. Use it when a keyword engine returns the wrong thing: conceptual questions, 'pages like this one', o...
Use to probe a URL for live HTTP status, final URL, redirects, content-type, and whether the response is HTML. Does not return the page body.
Use to list links on a page as structured rows: url, title, desc, rel, nofollow, internal/external, and kind. Not cleaned article body. An empty page returns item error no_links. After filter and dedupe, all unique links...
Use to fetch page metadata from a URL: title, description, Open Graph, favicon, HTTP status, and content type. Optional main-content text. One URL or items[]. Not article text (Web Content Cleaner) and not a link list (L...
Current web search results with titles, URLs, snippets, and source engine metadata.
Read any public URL as clean Markdown for an LLM: articles, docs, product pages, news, PDFs (text by page), RSS feeds and JSON. Real tables, code with language, math as TeX, absolute links; author, publish date and other...
Fetch one web page and return its main content as clean Markdown with title and word count, extracted server-side. Private and loopback targets are refused. Use this when an agent needs to read a page inside a workflow w...
Ask a question and get a written answer with the sources it was drawn from. The engine searches its index, reads the pages and composes the answer, returning the citation list (title, URL, published date) alongside it so...