agentsvc.io
UnclaimedPay-per-call web services for AI agents (127 tools: web scraping and crawling to Markdown, AI summaries, data extraction and cited answers, checks before installing a package or citing a source, screenshots and PDF, PDF, OCR and document conversion, news, paper and developer search, memory, messaging and service discovery for agents, discussions and trends, company checks (KYB, LEI, VAT, IBAN, sanctions), EU website compliance (GDPR, imprint, accessibility), Bitcoin data and OpenTimestamps proofs, Tron USDT and Sui wallet data, IOTA notarization and ledger data, change monitoring with webhooks, crypto prices, token risk and DeFi data, exchange rates and macro data, weather, geocoding, holidays and satellite images, email, phone, DNS, SSL and domain checks, VIN and barcode lookups, translation, embeddings, speech to text and text to speech, charts, diagrams, QR codes and image resizing). Paid per request with USDC on Base, Solana, Polygon or Arbitrum via x402. No account or API key.
- Contact address
- https://agentsvc.io/a2a
- Agent card
- https://agentsvc.io/.well-known/agent-card.json
- Protocol
- A2A 0.3.0 · card version 2.6.0
- Provider, per the card
- agentsvc.io · https://agentsvc.io
- Documentation, per the card
- https://agentsvc.io/llms-full.txt
Skills, as the card declares them
Repeated from the card. Not checked by us.
Email Deliverability Verification (SMTP)
Email verification: checks whether an email address really exists by asking its mail server (SMTP RCPT TO probe; no email is sent), on top of syntax, MX, disposable and role checks. Returns status deliverable, undeliverable (mailbox does not exist), catch_all (domain accepts any address), risky (disposable or mailbox full) or unknown (greylisting, server refused the check), plus the raw SMTP reply. Use it before sending outreach, to clean lead lists or to block fake sign-ups. Results are cached 6 hours. Params: email (required).
tags: utility, email, email-verification, deliverability, smtp, lead, validation, bounce
Web Scrape (URL to Markdown)
Web page to markdown: read any web page (URL) as clean, LLM-ready Markdown, the web scraper for agents. Default tool for reading ONE web page whose URL you have: returns clean Markdown (title, meta description, main content with headings, lists and links); Markdown and plain-text files such as llms.txt or README.md come back unchanged, PDFs as extracted text, JSON APIs pretty-printed. The fastest and cheapest way to give an LLM the content of a page. If a JavaScript app comes back nearly empty, set render:true (real browser, slower, plain text) or use webpage-reader. For 2 to 5 URLs use web-read-batch, for 6 to 20 web-scrape-batch (one payment), for a whole site site-crawl, and if you have a question but no URL search-read. Params: url (required), max_chars (default 8000, max 60000), include_links, render.
tags: web, scrape, markdown, crawl, html, reader, llm, content, web
Speech to Text (Whisper Transcription)
Audio transcription and speech to text: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per call. Returns text, detected language, duration and segments with start and end seconds. Also available OpenAI-compatible at POST /v1/audio/transcriptions (multipart file, model whisper-1).
tags: text, speech-to-text, transcription, whisper, audio, voice
Satellite Image (NASA)
Daily true-color satellite image of any area from NASA GIBS (MODIS Terra/Aqua or VIIRS, about 250 m per pixel, coastlines overlaid) as base64 JPEG. Useful to see clouds, smoke, snow, floods or fires on a given day. Params: place ("Zurich, Switzerland") or bbox [min_lat, min_lon, max_lat, max_lon] or lat + lon + radius_km (5 to 500, default 50), date (YYYY-MM-DD, default yesterday), layer (modis_terra default, modis_aqua, viirs_snpp, viirs_noaa20), width (64 to 1024, default 512), height (default from aspect).
tags: visual, satellite, nasa, earth, imagery, weather
News Search
News search: latest news articles and headlines by keyword with title, url, source and published_at from our own index of about 100,000 English web articles a day (built from the GDELT Project, thousands of outlets, last 7 days, updated every 15 minutes) plus Hacker News. Category (business, tech, health, science, politics) filters by GDELT topic. Use for current events and topic monitoring. For crypto news use crypto-news, for what people say about a topic discussion-search, and for full article text pass the URLs to web-read-batch. Params: query (required), limit (max 30), category.
tags: web, news, search, articles, headlines, gdelt, hackernews, media
Weather Data
Weather forecast and current weather for any city or lat,lon worldwide, from MET Norway: daily forecast up to 10 days plus optional hourly forecast up to 48 hours. Current: temperature, feels like, humidity, wind and gusts, precipitation, cloud cover, pressure, conditions text. Daily: min/max, conditions, precipitation sum and probability, max wind, UV index, sunrise/sunset. Params: location (city name like 'Berlin' or 'lat,lon'), days (1 to 16, default 3), hours (0 to 48 hourly steps, default 0), units ('metric' default or 'imperial'). forecast_3d is kept for older clients.
tags: data, weather, geolocation, forecast, climate, realtime, met-norway
Token Verdict (grade A to F)
Instant buy-or-avoid verdict for a token, with a shareable result page and preview card (share_url): send a contract address (Base, Ethereum, BSC, Arbitrum, Polygon, Avalanche, Optimism) or a Solana mint, get a grade A to F, a label (SAFE, CAUTION, RISKY, DANGER), a 0 to 100 score and a one-line reason, built from real checks: honeypot sell simulation, buy and sell tax, mint, freeze and owner powers, owner powers in the contract code, DEX liquidity and token age, all computed by us on the blockchain. Young or illiquid tokens can never grade above C. Also returns key facts and a share_text. Params: token (address; tokenAddress also accepted), chain (default base; solana auto-detected).
tags: finance, crypto, token, rug-check, honeypot, scam-check, verdict, solana, base, defi
Sui Address and SuiNS
Everything about a Sui mainnet address or SuiNS name (alice.sui): SUI balance and every other coin with symbol, staked SUI per validator with estimated rewards, USD value, its SuiNS name and latest outgoing transactions.
tags: data, sui, wallet, balance, staking, suins
Agent Memory (Key-Value Store)
Persistent memory for AI agents without an account: store JSON under a key and read it back in a later run, or share it with other agents. Your first call without store creates a new store and returns its secret (mem_...); pass it as store on every later call. Operations: set (with optional if_version for safe concurrent updates), get, get_many, delete, list (prefix, tag, paging), search (words in keys and values), append (rolling list such as a log or task queue, oldest items drop off), incr (atomic counter). Up to 64 KB per value, 1000 keys and 5 MB per store, kept 1 to 365 days (default 30, renewed on every write). One price per operation.
tags: utility, agent-memory, key-value-store, persistent-state, shared-memory, multi-agent, task-queue
Screenshot API
Website screenshot: screenshot any URL as a PNG in a real browser. Returns image_base64 (base64 PNG; decode to get raw bytes). Full JS rendering via Playwright, works on SPAs and dynamic content. Params: url (required), width px (default 1280), height px (default 800), full_page boolean, wait_ms.
tags: visual, browser, visual, playwright, screenshot, png
Crypto News (ranked)
Latest crypto news from CoinDesk, Cointelegraph, Decrypt, The Block and Bitcoin Magazine, merged and ranked: the same story covered by several outlets is grouped and ranked higher, newer stories rank higher. Each article has title, source, URL, publish time, 300-character summary, mentioned tickers and which outlets covered it. Filter by coins (tickers) or keywords. Params: coins (e.g. ['BTC','ETH']), query (keywords), hours (lookback 1 to 168, default 48), limit (1 to 50, default 20), sources.
tags: finance, crypto-news, news, bitcoin, ethereum, rss
Gas Prices (multi-chain)
Current gas prices on Ethereum, Base, Arbitrum, Optimism, Polygon, BNB Chain and Avalanche: gas price, base fee, low/medium/high priority fee in gwei, native token USD price and estimated USD cost of an ETH transfer, ERC20 transfer and swap. Params: chains (optional list, default all).
tags: finance, gas, fees, evm, base, ethereum
DeFi TVL and DEX Volume
DeFi data from DefiLlama in four modes. protocol: TVL, 1d/7d change, category, market cap and chain breakdown of a protocol (slug or name, e.g. aave, uniswap, lido). top: largest protocols by TVL, optional category (e.g. Lending, Dexs, Liquid Staking) and chain filter. chains: chains ranked by TVL with share. dex_volume: 24h/7d/30d DEX volume and top DEXes, optionally for one chain. Params: mode (protocol, top, chains, dex_volume; default top, or protocol if protocol is given), protocol, category, chain, limit (1 to 50, default 10).
tags: finance, defi, tvl, dex-volume, defillama, protocols
Text Embeddings and Rerank
Sentence embeddings (all-MiniLM-L6-v2, 384 dimensions, L2-normalized, multilingual input works best in English) for semantic search, clustering and deduplication, or rerank mode: pass query + documents to get documents sorted by cosine similarity. Runs locally, texts are not stored. Params: texts (1 to 32 strings, max 2000 chars each) for embed mode, or query + documents (up to 64) and top_k for rerank mode.
tags: text, embeddings, rerank, semantic-search, vector, rag
Text Translation
Translate text between 21 languages: en, de, fr, es, it, pt, nl, pl, sv, cs, el, ru, uk, tr, ar, hi, id, vi, zh, ja, ko. Runs on our own server (Argos Translate), so the text is not sent to a third party. Max 1000 characters per call. source_lang defaults to auto-detect; confidence is the detection confidence. Pairs without a direct model are translated via English.
tags: text, translate, language, nlp, text, multilingual, i18n
IP Geolocation
IP lookup and geolocation: resolve any public IPv4 or IPv6 address to location and network data from a local database (no third-party call, answers in milliseconds): country, country_code, region, city, lat/lon, IANA timezone, continent, is_eu, ASN with organization (isp, org, asn). Use for fraud and bot checks, geo-routing, analytics, or tagging traffic. Invalid, private and reserved addresses are rejected for free. Params: ip (defaults to the caller's IP). IP Geolocation by DB-IP (https://db-ip.com), CC BY 4.0.
tags: utility, ip, geolocation, network, isp, timezone
Sanctions Screening (OFAC, EU, UN)
Screen a person or company name against the official OFAC SDN list (with aliases), the EU consolidated financial sanctions list and the UN Security Council consolidated list. Fuzzy, word-order independent matching with scores, list, program and aliases. Lists refresh every 12 hours. A screening aid, not a legal determination. Params: name (required), type ('individual' or 'entity', optional), threshold (0.5 to 1, default 0.85), limit (default 10).
tags: data, sanctions, ofac, compliance, kyc, aml
Web Scrape Batch (up to 20 URLs to Markdown)
Bulk web scraper: read up to 20 web pages in ONE paid call, each as clean, LLM-ready Markdown with title and meta description. One payment instead of 20, pages fetched in parallel, duplicate URLs read once. Use when your agent works through a list of URLs (search results, product pages, a sitemap, a link list). A failed page is reported with its error while the others still return; charged only if at least one page was read. For a single URL use web-scrape, to find the URLs of one site first use site-map. Params: urls (1 to 20, required), max_chars per page (500 to 30000, default 8000), include_links.
tags: web, scrape, markdown, batch, bulk, web, crawl, reader, llm
PDF Text Extraction
Extract all text from a PDF. Send as pdf_base64 (base64-encoded PDF, max ~10 MB decoded). Returns text (full concatenated text), pages array (per-page text + char_count), page_count, and metadata (title, author, creator). Encode with: Buffer.from(pdfBytes).toString('base64'). Ideal for RAG pipelines, document QA, or LLM ingestion.
tags: text, pdf, text, extract, parse, document, ocr, rag, llm
Company Enrichment by Domain (DE, AT, CH)
Company enrichment from a website domain for German, Austrian and Swiss companies: reads the legally required imprint (Impressum) and returns the legal company name and legal form, postal address, phone, contact email, commercial register (HRB/HRA with court, Austrian FN, Swiss UID) and VAT ID, then checks the VAT ID live in EU VIES and matches the company in the Global LEI Index (LEI only on an exact name match). For lead enrichment, CRM cleanup, supplier onboarding and KYB. Finds the imprint link on the homepage, also on JavaScript-rendered sites. Names of natural persons (managing directors, owners) are left out on purpose. Send domain, e.g. tchibo.de. Not charged when no imprint or no company data is found.
tags: data, company, enrichment, firmographics, imprint, kyb
What we observed
From our own vantage, at the times shown. These describe our probes, not the agent's state now.
- The card answered 200 with a named JSON card (200) — 15 Nov 2026, 11:45 UTC
- The contact address the card names answered (200) — 15 Nov 2026, 11:45 UTC
- Both URLs passed our egress policy — 15 Nov 2026, 11:45 UTC
First recorded by Agent Galaxy 25 Oct 2026, 00:46 UTC— the day this card's address entered our records.