Web Search Research x402 offerings

Get Google Extended Reviews Completed Tasks

skills: {'id': 'check_health', 'name': 'Check Health', 'description': 'Site availability, robots.txt, AI crawler access (GPTBot, ClaudeBot, PerplexityBot), sitemap presence', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_llms_txt', 'name': 'Check Llms Txt', 'description': 'llms.txt existence and quality check: sections, links, statistics', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_schema', 'name': 'Check Schema', 'description': 'Schema.org JSON-LD detection: types found, FAQ schema, Organization schema', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_agent_files', 'name': 'Check Agent Files', 'description': 'openapi.json, ai-plugin.json, x402 payment support detection', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_mcp', 'name': 'Check Mcp', 'description': 'MCP discoverability: /.well-known/mcp.json, agent.json, MCP Server Card', 'tags': ['audit', 'mcp', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'score_aeo', 'name': 'Score Aeo', 'description': 'Full AEO (AI Search Visibility) score 0-100 with detailed checks', 'tags': ['score', 'ai', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'score_geo', 'name': 'Score Geo', 'description': 'Full GEO (Citation Readiness) score 0-100 with detailed checks', 'tags': ['score', 'ai', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'score_agent', 'name': 'Score Agent', 'description': 'Full Agent Readiness score 0-100 with detailed checks', 'tags': ['score', 'ai', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}; conformance: fail

Scrape and extract clean text/markdown from a public URL for agent pipelines on Venice, paid per request in USDC on Base via x402, no API key. Standalone; no model lookup required.

Web search for agent pipelines on Venice — ranked results for a query, paid per request in USDC on Base via x402, no API key. Standalone; no model lookup required.

AI-industry stories independently reported by two or more outlets, with the corroborating source URLs, outlet names and first-seen timestamp for each

Free preview first: add ?preview=true for the response shape, no payment. Paid: ranked full-text search over every published PXke Algorand article. Up to 50 hits with title, summary, snippet, URL and the id/slug for the free article route; fewer than `limit` matches are topped up with the newest articles ("match": "recent"). Params: q (required), limit. (USDC preferred; EURQ, USDQ, and goBTC also accepted.)

Text summarization API: summarize any text or article (English, French, any language, 200 to 7,000 characters) into a faithful 5-8 sentence summary / TL;DR. No API key, pay per call.

Convert any webpage URL into clean, ad-free Markdown text optimized for LLM context windows. Paid in USDC on Base.

Our weekly census of 65,000 top sites: how many sites and stores publish UCP or ACP agent-checkout profiles, agent and MCP cards and llms.txt, which AI crawlers stores block, store platforms, and changes in the last 30 days. With signal=, the stores that have it (for example signal=ucp), most-linked first. Signed.

Cited answer (RAG): a natural-language question is answered by searching the public web, reading the top pages and synthesizing a grounded answer with a list of source URLs. Answer cites only the retrieved sources (anti-hallucination).

Cited answer (RAG): a natural-language question is answered by searching the public web, reading the top pages and synthesizing a grounded answer with a list of source URLs. Answer cites only the retrieved sources (anti-hallucination).

Answer with sources: ask a question, get a short answer with numbered citations [1], [2] and the source list. Searches Wikipedia and our own news index (GDELT and Hacker News, last 7 days), reads the top 3 pages and answers only from them with Claude Haiku 5.5; when the sources do not answer the question it says so. source auto (current events go to news first), news or web (Wikipedia); optional answer language.

Extract and classify links from one public page or safely crawl up to 10 same-origin pages into an agent-ready site map with page provenance, depth limits, and robots.txt enforcement.

Fetch and normalize public RSS or Atom feeds into stable structured JSON entries for agents and research workflows.

Extract webpage metadata from one public URL: page title, meta description, canonical URL, headings, hreflang, icons, feeds, Open Graph, Twitter Cards, and JSON-LD Schema.org types, with redirect and response provenance plus privacy-safe, publisher-asserted Organization facts with field evidence.

Convert and extract a public website URL into clean Markdown or readable text plus bounded structured links, canonical and heading signals, Schema.org types, redirect evidence, content hashes, and response provenance for RAG, research, or agent context.

Fresh operational audit of any public agent or paid API: reachability, latency, HTTP status, x402 challenge, price/network/payTo, OpenAPI, agent card and MCP manifest. Returns a 0-100 score, verdict and issues. Try GET /agent-health/sample.

Convert a Twitter/X, LinkedIn, Medium, Substack, Beehiiv, or public Notion page URL into clean markdown.

Web scraping proxy API - send a URL, get clean markdown or HTML content back. Supports dynamic rendering.

Web scraping proxy API - send a URL, get clean markdown or HTML content back. Supports dynamic rendering.

Web search API for agents: search the web and get result titles, URLs and snippets as JSON

URL extract with a question: ask any web page a question and get structured data as JSON that matches your schema

[Deprecated - use websearch_search_web] Enqueues a websearch_search_web job and returns a task id immediately

Fetch a web page and return a concise summary and key points (SSRF-safe fetch + Claude).