Get Prediction Market Top Holders

Max memecoin holder trace (Solana pump.fun, Base): 60 early buyers, 2 funding hops, exchange hubs excluded, plus the creator's track record (how many tokens it launched, how they ended, serial launcher flag) and insider rings: early buyers who were also early in the same creator's other launches, told apart from generic sniper bots.

24-hour memecoin watch with alerts: we re-run your screen strategy (alert on every new matching token) or your position exit rules (alert when hold turns into sell / exit, gain milestones) every 5m, 15m, 30m, 1h, 4h or 1d; positions also every 1m, with a sell-burst dump detector. Alerts: free to read with the watch id, POSTed to your webhook, or sent to your Telegram bot / Discord channel.

MAX tier (bigger runs than the $0.03 version: 15 companies). LinkedIn company data from URLs, names or domains: description, website, industry, size, employees, HQ, founded, specialties, followers, locations, similar companies and recent posts with likes and comments. No login, no personal profiles. Result caps in the input schema; failed lookups are not charged.

Pay-per-call: Email Deliverability

Prop-firm challenge audit from your own trades: pass odds (raw, robust with luck removed, from where you stand), edge or luck, consistency grade A-F, and a coach that runs 19 live-trading gates on every trade (rollover, revenge, oversize, stacking, currency overlap, swept stops...). Send an FTMO trading-journal CSV or a terminal export. Returns JSON + a dashboard link.

Full token due diligence in one call (EVM or Solana): contract / mint safety (honeypot simulation, taxes, mint and freeze authority, Token-2022 traps), pre-trade verdict, market and rug-risk %, and for pump.fun or Base tokens the max holder trace (bundles, insiders, creator's other launches). One verdict, every red flag, a plain summary.

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 from several sites, not one snippet.

MAX tier (bigger runs than the $0.04 version: 3 keywords, 2 locations, maxJobs up to 100). Scrape LinkedIn job listings by keyword and location (date, remote/hybrid, job type, experience filters): title, company, location, salary, full description, seniority, employment type, applicants, plus department and tech stack. No login. Result caps in the input schema; failed lookups are not charged.

Pay-per-call: IP Geolocation

MAX tier (bigger runs than the $0.04 version: 3 keywords, 2 locations, maxJobs up to 200). Scrape Indeed jobs in 35 countries by keyword and location (date, job type, remote, radius filters): full description, salary (annualized), skills, Easy Apply, plus employer website, size, revenue and tech stack. No login. Result caps in the input schema; failed lookups are not charged.

Official Swiss company registry lookup (Zefix). Query: /v1/eu/entreprise/CH/CHE-107.480.920 (UID, dots optional). Returns legal name, legal form, normalized status, registered office, cantonal register link, live from Zefix. 404, not billed: a Swiss sole proprietorship (Einzelunternehmen), a branch whose head office is not served, an undecided form. Same unified schema as every Sirenic European profile.

MAX tier (bigger runs than the $0.04 version: 5 videos, maxCommentsPerVideo up to 500, maxRepliesPerComment up to 20). Scrape YouTube comments from any videos: top or newest, with replies, likes, reply counts, author and channel id, pinned/hearted, publish time, direct comment links. No API key, no quota. Cheap per comment. Result caps in the input schema; failed lookups are not charged.

What changed at a French company since a date (?depuis=YYYY-MM-DD), every official block in one call: BODACC notices (insolvency, sales, accounts filings with their figures), commercial-court decisions, public contracts (DECP, TED), establishments, cessation, licences, dated sanctions listings, trademarks and patents, RGE, lobbying register. Dated at publication, event date alongside; verdict nouveautes, rien_de_nouveau or lecture_incomplete; 100 most recent.

Crypto market sentiment: the Fear & Greed Index (0=extreme fear, 100=extreme greed) with classification, plus optional history. Query: days (1-90, default 7). Use as a contrarian signal, regime filter, or risk gauge in trading loops.

Hand off a whole research or lookup task in one call: a Claude Haiku 5.5 agent plans the steps, calls up to 38 agentsvc.io tools in parallel (web and news search, page reading, papers, GitHub and npm, company registers and sanctions, crypto prices, token checks, DeFi TVL and yields, wallets, FX and macro data, weather, DNS, WHOIS, SSL, CVEs) and returns a Markdown answer with sources and the list of tool calls it made. Up to 12 steps and about 90 seconds.

Full EU company check in one call: LEI entity status, VAT validation (VIES), sanctions screening, domain age and email security, website, optional IBAN. Returns grade A to F, score 0 to 100, ALLOW, CAUTION or BLOCK, the reasons, a confidence level and the underlying sections. Pass name and at least one of vat_number, lei, domain. Use for onboarding and payment checks. Not legal advice; a sanctions match is a hint to verify by hand.

EU public procurement awards won by a company from Latvia, Lithuania, Norway, Belgium, Denmark, Finland, Sweden, Czechia, Slovakia or Estonia, from TED, matched by NATIONAL ID in each form: buyer, country, subject, notice-level amount, CPV, link, co-winners proven legal persons (others counted). 40-94% of award notices carry a readable winner ID: zero is non-conclusive. BE, CZ, DK, EE, LT, LV, NO, SK: legal persons only, else 404, not billed. Also FI off-list forms. Live TED, cache 24 h.

7-day memecoin watch (max tier): your screen strategy or position exit rules re-checked as often as every minute (strategies too), for a week. Alerts as JSON, webhook, Telegram bot or Discord channel; milestones and the sell-burst dump detector included.

MAX tier (bigger runs than the $0.08 version: 1 searchTerms, 2 locations, maxPlacesPerSearch up to 60, maxContactPages up to 2). Scrape Google Maps places by search term and location: name, category, address, coordinates, rating, reviews count, phone, website, opening hours, attributes, place ID, plus optional emails and social profiles from each website. Fast, no API key. Result caps in the input schema; failed lookups are not charged.