Search & web

Image search API - live Google Images results for a query, localised by location and language. Returns ranked images with title, direct image URL, source page URL and alt text. A google images / image search api for agents.

Legal entity reference data from the GLEIF LEI golden copy (updated daily, CC0). Direct lookup: ?lei=529900FCMZ4LKXFD0R69. Search: ?name=airbus&country=FR&limit=5. Each result: lei, legal_name, entity_status, registration_status (ISSUED/LAPSED), jurisdiction, legal_form_id, hq_city/country, next_renewal_date. 24h cache.

+1 more from eu-verify

Provider cost + 6%, itemized. Pull requested fields out of any text as clean JSON — schema-shaped output. ≈Opus-4.8 accuracy at ~1–5% of its cost (relaystation.ai/llm-validation). One of 11 vetted sub-cent LLM tasks on Relaystation — 155 tools, one balance.

$0.005/extract. Extract the clean article text — title, byline, body — from any public URL. No boilerplate, no nav junk. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

Agent Research Trace Report performs a bounded deterministic agent research trace report operation over caller-supplied AI and search evidence.

$0.08/document. Pull tables out of a document as structured rows and columns (Textract Tables) — not text soup. 155 tools, one balance — relaystation.ai

$0.28/document. Extract form fields as key→value pairs from scanned or digital documents (Textract Forms) — structured JSON out, no template needed. 155 tools, one balance — relaystation.ai

$0.0003/MP. Extract N evenly-sampled frames from a video — a manifest of presigned image links back. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

Convert a public webpage URL into clean, LLM-ready Markdown for AI agents, research, RAG, extraction, and downstream processing.

Seenly Video Pitch Kit: resume to 45-60s video-pitch script (+15s cut, headline, strengths, captions)

Bundled execution of the Answer-a-question with sources workflow - The 'research a question, return an answer with citations' workflow. Brave answer for the AI-synthesized take with citations, Brave web for the canonical SERP, Brave news for time-sensitive context, then a deterministic web-fetch + extract pass on the top citations to verify the answer hasn't hallucinated. Five tools, one cited paragraph, every claim traced back to a fetched URL.

Fuzzy-search countries, currencies and languages by name or code. Scope with `registry` (defaults to all). Matches are ranked exact-code/name → prefix → substring.

Search the periodic table by name or symbol substring. Exact matches rank first, then prefix matches, then substring matches. Returns up to `limit` elements (default 20) plus the total match count.

Paid ($0.02 USDC via x402). Raw scraped content items from the last 4 hours across all Pulse sources. Proxied from the Pulse service. Compute-first / settle-after — you are never charged when Pulse is unavailable or returns an error.

Launch announcement for AI agents: give a product URL, get a ~400-word AP-style press release drafted from the page and published on a public, search-indexed newsroom page (IndexNow ping to Bing/Yandex included). Synchronous, ~20s. You are only charged if the release is produced.

COMEX warehouse inventory: registered, eligible and total levels plus the per-depository breakdown, by metal and date. Quantities are in CME's reporting unit per metal: troy ounces for gold/silver/platinum/palladium, SHORT TONS for copper, metric tonnes for aluminum/zinc/lead. Extracted from CME's daily warehouse PDFs.

POST a URL; get clean, LLM-ready content (Markdown/text/JSON) plus a prompt-injection risk verdict (clean | suspicious | flagged). A defense layer for agents and RAG pipelines, not a guarantee.

Web content extraction and search. Get clean markdown from any URL or search results.

Fuzzy-search airports by name, city or code, optionally filtered by ISO country code or airport type. Matches are ranked exact-code/name then prefix then substring, larger airports first. Empty result is a successful 200.

Encode a word with the Metaphone algorithm — more accurate than Soundex for English pronunciation.

Validate a ULID and extract its embedded timestamp and time/random components.

Fuzzy-search emoji by name, shortcode or keyword tag, ranked exact → prefix → substring.

Search the constants table by key, symbol or name substring. Exact matches rank first, then prefix matches, then substring matches. Returns up to `limit` constants (default 20) plus the total match count.

AI Web Extractor — turn ANY url into clean, LLM-ready markdown. POST {url}; get the main content as markdown (boilerplate/nav/ads stripped) with title, description, and links. The scrape / read / url-to-markdown primitive for RAG and research agents. Fast, cheap, x402-native.

Use when an agent needs to read web pages: clean markdown plus rich page metadata (title, description, OG image, canonical URL, author, reading time). Supports max_length. $0.002 per URL; pass up to 10 comma-separated URLs in 'urls' for batched calls. Not charged if all fail.

+2 more from x402 tools

Extracts sanitized, boilerplate-free markdown and clean text from web URLs with strict private network SSRF safeguards.

+5 more from dt0ur.online

Extract tables present in supplied text into a structured representation; preserve values and flag ambiguous cells. Uses buyer-supplied information only; no external research or outbound actions. Returns a draft for human review.

+11 more from tradepilotusa.com

Token search

+1 more from api.arcgate.dev

Full agent-readiness report for a website or API: everything in the readiness audit plus a quality review of the agent card, OpenAPI document, llms.txt, MCP server (connects, tools, descriptions) and pay-per-call manifest (does a listed endpoint really answer 402), CORS for in-browser agents, and an AI-written prioritised fix plan.

+2 more from api.manylives.me