Web & Data

Sends a prompt to N models, returns consensus + disagreement flags. For high-...

Verify the deliverability of an email address.

Fetch Web Page as Text: fetch any public URL as clean readable text Executed deterministically by the AmanChain node against live consensus state (real blocks, pools, balances) — paid per call via x402, settled in USDC on Base. Input: JSON body {"serviceId":"aman-web-fetch","request":" "}. No account, no API key.

Returns a computed disruption score, total events, top industries, and the largest filings within a radius (up to 500 miles) of a ZIP — use it to size territory-wide workforce risk

query -> structured search results (title, url, snippet), up to 10 per call. Backed by three providers with automatic failover (DataForSEO primary, Tavily and Serper as fallback) so a single provider outage doesn't take the endpoint down. Pass region=tw for a Traditional Chinese / Taiwan-region search lane. Results are cached for 24 hours per query+region.

Returns repo, total_neighbors, and the neighbor list for one repository. Returns 404 if the repository is unknown.

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

Single-fact: Zcash mempool count + bytes.

Screen untrusted text against known prompt-injection patterns (pattern matching, not a model). Returns which named patterns matched.

Performs web searches and returns results from indexed online sources.

Amazon Shop

Lite know-your-business check on a French company: legal existence, current administrative status and any insolvency flag. The minimum an agent needs to decide whether a counterparty is real and active before going further. Upgrade to /v1/fr/kyb for directors, beneficial owners and the full compliance dossier.

Real-time fishing & outdoor conditions scored 0-100. Water temp, tide, wind, species intel.

Grounded web search: question → answer + citations, powered by Bedrock Web Search.

Analyze a public webpage and return title, description, headings, word count, links, emails, social links, and page metadata.

Extracts content from web pages by parsing and retrieving data from specified URLs.

Get the current time, date, and timezone for a location.

Get the current time, date, and timezone for a location.

Read up to 5 web pages in one call and get each as clean Markdown with title and description. Pages are fetched in parallel; a page that fails is reported with its error while the others still return. Charged only if at least one page could be read. Params: urls (array of 1 to 5 http(s) URLs, required), max_chars per page (500 to 30000, default 6000).

Processes multiple search queries in a single request.

Fetch a public web page and return clean readable text with its title and metadata - the form a model can actually use, with navigation, scripts and styling removed. Follows up to 3 redirects, caps the download at 2000000 bytes and gives up after 15000ms. Reaches the PUBLIC internet only: the hostname is resolved and every redirect hop re-checked against private, loopback, link-local and CGNAT ranges, so this cannot read internal services or cloud metadata. Returns raw HTML too on request.

Search the healthcare vocabularies loaded on this deployment and get codes back with a MEASURED confidence and full provenance: which dataset, loaded from where, under which licence, and whether it is synthetic. The scoring function is documented on every response (exact code 1.00, exact display 0.95, exact synonym 0.90, prefix 0.60-0.85, token overlap 0.30-0.75) rather than being an opaque number.

Emit the actual files that fix a site's AI legibility, ready to deploy: a real /llms.txt, a /robots.txt that stops excluding AI crawlers (with a unified diff against the current one), and a JSON-LD block for the page . Nothing is invented: every link in the llms.txt is discovered on the site and then FETCHED to confirm it answers 200, with failures dropped and counted, and every JSON-LD field is copied from something the page actually declares — anything that cannot be grounded is…

Full-text search over what machine-payable services actually publish — their descriptions, input schemas, parameter names, prices and settlement networks — across ~18,000 x402 endpoints. Built from their own payment challenges, which a general crawler discards as a dead page: ask for a parameter name, a schema field or a network and you match services whose one-line blurb never mentions it. Filter by price ceiling, by whether the service publishes a call spec, and by payment protocol.