93 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.
TableGrab: give a public URL and get clean, typed JSON tables (headers, row objects, inferred column types, caption/heading context; colspan/rowspan handled; ISO dates and real numbers) or the page's main content as Mark...
Data Quality Gate: deterministic dataset quality verdict
Argentina official gazette (Boletin Oficial) keyword search returning literal excerpts of matching notices with dates and source URLs; an optional date limits the search to that day's notices. Use this when an agent need...
Audit text for malicious AI-skill patterns. Requires `content`. Nothing to audit — crawling, or discovering this endpoint cold? POST /audit/registry runs the same scanner over the newest servers in the official MCP regis...
Use when a Brazilian postal code needs to become a real address — filling a form, validating a delivery, completing a customer record. JSON body { cep } (8 digits). Returns street, complement, neighborhood, city and stat...
Fetch a public https page and return its HTML tables as header and row arrays, with captions and row/column spans resolved.
Heuristic main-content extraction from supplied HTML by text density and tag scoring; returns text, title, byline, confidence.
Compare two to four product pages by verified identity, listed price, availability, shipping cost and rating without converting currencies.
Fetch any public webpage and get just its readable text (no HTML, scripts or styles) plus title and meta description, ready for an LLM context window. Optional max_chars cap. Returns 404 if the page is missing, 502 if bl...
Current weather + multi-day forecast for any city or lat/lon via Open-Meteo. Temperature, humidity, wind, precipitation, WMO condition codes.
URL to Markdown API for AI agents. Converts a public web page into clean Markdown for LLMs and RAG pipelines: main content only (no nav, ads or scripts), absolute links, plus title, description and language metadata. Sui...
Checksum tier (deterministic, no LLM): verifies the exact bytes served at a public URL hash to a claimed sha256, by independent double re-fetch. Use it to confirm a download or artifact matches its published checksum. Bo...
LLM chat completion (probe endpoint). Use POST to send a chat request.
HTML table to JSON. Extract every table from an HTML fragment into JSON: header cells become keys and each body row an object (or raw arrays when there is no header row), with captions, colspans repeated and entities dec...
PDFs, JavaScript pages and ordinary HTML as clean Markdown. Pays a page's x402 toll for you. Follows robots.txt.
Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; mark...
Use when you need what a web page says: read a public web page as clean text for an AI agent: title, description, main text (scripts, styles and navigation removed) and links. Respects robots.txt.
Web-content reader: fetch any http(s) URL and return clean readable text, title/description/canonical, and outbound links as JSON — the data an agent ingests on each step of a crawl or RAG loop. Input: url.
Scrape website page to Markdown. Fetch any public web page URL and get clean, LLM-ready text or Markdown: main content, code blocks, tables, links and headings, for RAG and agent context. Static HTML, Markdown or text; o...
Read multiple web pages for AI agents: give up to 5 URLs, get the full clean text of each page, rendered in a real browser so JavaScript sites work, with title and final URL, in one call and one payment. For RAG, researc...
Base Latest Block: current Base mainnet block number, timestamp, base fee and gas used. $0.001 per call.
Token verdict / rug check: an A-F safety grade, a one-line verdict and a plain-language take on any token on Base, Ethereum, BSC, Arbitrum, Optimism, Polygon, Avalanche or Solana, with a shareable page and card image. Bu...
Compare a web page across countries. Compare one public page across 2-5 countries in one call: status, redirect, language, extracted product price converted to USD, and an excerpt (or full content) per country, plus the...
Parse a site's robots.txt: whether a user-agent may crawl a path, which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot...) are blocked, and declared sitemaps. Check before your agent scrapes.