Tariffmonkee

A2A (Agent2Agent) protocol JSON-RPC endpoint, SendMessage only. Authorizes up to $0.75 (the highest-priced skill); settlement charges the invoked skill's real per-skill price. Base (EVM) only -- for Solana use the REST or MCP endpoints. See /.well-known/agent-card.json for the skill catalog and per-skill pricing.

Fetch a URL with a real rendered browser (JavaScript executed) and return clean Markdown. Results are cached for 24 hours per URL, so repeat calls for the same page are fast and don't re-render.

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.

Fetch a URL with a real rendered browser and extract structured data from it in one call, using AI (tries multiple models in sequence for reliability). Use this when you don't already have the page content; use the cheaper /extract if you do. Results are cached for 24 hours per URL+schema combination.

URL -> safety verdict. Checks the redirect chain, detects homograph/punycode hostname tricks, and cross-references the destination host against the URLhaus threat feed. Use to vet a single URL before fetching, sharing, or acting on it. For a full domain configuration grade use /sitegrade; for ownership/registration facts use /domain-intel.

Domain -> ownership and registration intelligence via RDAP. Returns registration age, registrar, privacy-proxy status, expiration date, nameservers, and detected mail provider. For technical configuration grading use /sitegrade; for URL-specific reputation use /linkcheck.

Extract structured data from content you already have (e.g. from a prior /content call), using AI. No browser render involved -- pure AI extraction, cheaper and faster than fetching a URL fresh. Use this when you already have the text; use /extract-url if you only have a URL.

Health and payment-path check. Returns server time and a confirmation that your x402 payment settled. Cheapest endpoint in the catalog; use it to verify your client's payment flow before calling paid tools.

Domain -> security letter grade (0-100, A-F) from HTTPS reachability, security headers (HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy), and CAA records. Reports HTTPS connect success/failure, not raw cert expiry -- Workers can't read a remote server's cert metadata directly. For registration facts use /domain-intel; for URL reputation use /linkcheck.

URL -> AI-readiness report. Checks schema.org structured data, crawlability (robots.txt, meta robots, canonical), and llms.txt presence, then returns a 0-100 score with specific recommendations for what's missing. Results are cached for 24 hours per URL.

Email address -> deliverability verdict. Checks syntax, MX record presence, disposable/temp-mail domain match, and SPF/DMARC presence on the domain. Scoped to a single address, not a full domain security audit.

Taiwan healthcare navigator: NHI-contracted institutions by county/specialty, current copay by facility tier and referral status, and NHI eligibility (the 6-month rule and its no-wait exceptions for employed and professional-talent-act cases). Routes to care and explains cost, not medical advice: no diagnosis, no doctor recommendation. English-language capability at a clinic is not an official NHIA field and is never reported here.

Discover and qualify local business leads by category and area -- no pre-existing list required. Searches Google Maps for the given category in the given area, then returns only businesses with at least one real red flag (unclaimed listing, missing photos, missing hours, missing website, low rating, or few reviews), as a CSV ready for cold outreach. Up to 10 qualified leads per call.

Fetch a URL with a real rendered browser (JavaScript executed) and return a PDF of the full page. Not JSON -- the response body is the file itself. Results are cached for 24 hours per URL. Cache status and fetch time are reported in the X-Cached and X-Fetched-At response headers.

query -> up to 10 deduped, rendered sources as one token-budgeted bundle (~8,000 tokens combined). Combines /search (three-provider failover, region=tw Taiwan lane) with /content's rendered-page fetching internally, so you get one call instead of assembling search-then-fetch yourself. Sources are deduped by domain. Requires at least 3 successfully fetched sources to succeed -- returns sources_requested and sources_returned so you can see how many of the candidate set actually came back.

Fetch a URL with a real rendered browser (JavaScript executed) and return a PNG screenshot of the full page. Not JSON -- the response body is the image itself. Results are cached for 24 hours per URL. Cache status and fetch time are reported in the X-Cached and X-Fetched-At response headers.

Keyword + domain -> search position. Checks whether and where a domain ranks in Google organic results for a given keyword, via the same DataForSEO SERP data already powering /search.

Orchestrated bundle: runs /linkcheck, /sitegrade, and /domain-intel (plus /email-verify if an email is supplied) and synthesizes one confidence-weighted trust verdict, explicitly flagging disagreement between sources -- e.g. a very new domain paired with an unusually mature TLS/header setup -- rather than just concatenating four outputs. Supply at least one of domain, url, or email.

White-label local visibility report for one business -- combines Google Business Profile completeness, organic search ranking for a target keyword, and AI answer-engine visibility for a buyer-intent query into a single PDF deliverable. White-label by design: no TariffMonkee branding anywhere in the report output, so agencies can present it under their own name to a client or prospect.

Business/domain + query -> does it appear in AI answers. Sends the real query to a live AI model with web search enabled and checks the actual response for a mention of the business and a citation linking to the domain.

Alias of /content for agents that call a single URL directly. Fetches a URL with a real rendered browser (JavaScript executed) and returns clean Markdown. Results are cached for 24 hours per URL.

Business -> visibility score, missing fields, review health, AI-readiness flags, fix list. Audits a Google Business Profile via DataForSEO's Business Data API: category, contact info, hours, claimed status, photos, and review rating/distribution.

Audit-qualified lead list for prospecting. Submit up to 10 candidate local businesses; each is checked against its Google Business Profile (claimed status, photos, hours, website, description, rating, review count) and only businesses with at least one real red flag are returned, as a CSV ready to use as a cold-outreach list. Cheaper per-business than calling /gbp-audit individually if you use the full batch.

Taiwan tax residency GUIDANCE, not tax advice, from arrival/departure dates and income. Determines resident (183+ days/year) vs non-resident using the official start-day-excluded, end-day-included counting rule; non-residents get the 6%/18% withholding threshold (1.5x basic wage); residents get an estimated tax owed using that year's brackets and deductions. DTA treaty rates and Alternative Minimum Tax are flagged, not computed. Only Taiwan's National Taxation Bureau determines final liability.

Taiwan work permit eligibility GUIDANCE, not a determination, for a foreign-professional profile. Checks the 2026 graduate Extended Stay exemption (no permit needed), the general professional route (Article 5 qualification plus the NT$47,971 salary floor), and reports points-route criteria and confirmed scoring bands as attributed reference without computing a total score, since the official per-band table is unverified. Only Taiwan's Ministry of Labor decides an actual application.