Weather forecast for a coordinate. Pick current/hourly/daily variables (temperature, wind, precipitation, humidity, …) and a timezone; returns the values plus their units.

Returns the current weather for a location identified by city name (q) or latitude/longitude, including temperature, feels-like, humidity, pressure, wind, cloud cover, visibility and a textual condition. Provide either q or both lat and lon. Metered per call via Apiosk (x402, USDC on Base).

API call to openweather

Search/filter individual news articles with query, date, source, country, language and topic filters.

Search AI-clustered news stories and summaries by topic, entity, location and time filters.

Forward geocoding: address/place -> coordinates.

Reverse geocoding: coordinates -> address.

Research a company by name (or domain) and return a standardized firmographics record merged from the company website and People Data Labs.

Enrich a single company from PeopleDataLabs. Provide a name, website, LinkedIn profile or ticker and get firmographics back (employee count, industry, location, founded, tags, etc.).

Enrich a single person from PeopleDataLabs. Provide any combination of identifiers (email, phone, LinkedIn profile, or name + company) and get a full professional profile back.

Search the PeopleDataLabs person dataset with SQL or an Elasticsearch query and get a list of matching people. `size` is capped at 25 (default 10) since PDL bills one credit per record returned.

Scrape a target URL. Returns the raw page content.

API call to serper

Google SERP data for a query.

Find ranked shipment options for a package using query-string parameters. Returns the cheapest and best-value carrier plus the full priced list. EUR 0.10 per call.

Extract web page content from one or more URLs.

Run a Tavily web search with optional answer, images and result-depth controls.

Compare a domain against a caller allowlist using edit distance and visual confusable skeleton similarity.

Detect mixed-script and confusable Unicode characters and return exact offending codepoints.

Apply NFKC normalization and remove zero-width and bidi override characters, returning cleaned text plus a removal report.

Check copy against brand rules: forbidden words/phrases, required terms that must appear, and preferred-term substitutions. Returns issues for violations plus suggested from->to replacements.

Independently re-compute order/invoice math from line items and optional fees, returning gross, fee and net so an agent's own totals can be verified against a trusted calculation.

Check a generated answer against a set of approved facts and forbidden claims to catch ungrounded or off-limits statements. Flags forbidden claims found in the answer and warns when the answer matches none of the approved facts.

Check an intended action — vendor, amount and category — against a spend policy (max amount, allowed/blocked vendors, allowed/blocked categories) before money moves. Returns allowed=false with reasons when any rule is violated.

Validate that a structured output contains the required fields and that each field has the expected JSON type. Returns valid=false plus a list of errors when a field is missing or mistyped.

FX rate for a currency pair, e.g. USD/JPY.

Latest price for a symbol (stock, ETF, forex pair or crypto pair).

Full quote for a symbol: open/high/low/close, volume, change, 52-week range and a market-open flag.

Historical OHLCV time series for a symbol at a chosen interval (1min…1month).

API call to twilio

Returns real-time current weather for a location (city name, decimal lat,lon, US/UK/Canada postal code, IATA airport code such as iata:DXB, or auto:ip), including temperature, wind, humidity, pressure, visibility, UV index, and optional air-quality data. Each call is metered and paid per request through Apiosk via x402 (USDC on Base).

API call to weatherapi

Return a short company description from a homepage: og:description > meta description > first meaningful paragraph. Cleaned, single-line, truncated to ~280 chars. Never invents text that is not on the page.

Extract emails, phone numbers, social links and contact URLs from a page. Known placeholder emails are filtered; a same-origin contact page is fetched for extra signal and merged (deduplicated).

Heuristically parse pricing plans (name, price, currency, billing period, features) from a pricing page. Each plan gets its own detected currency. Returns plans [] with confidence 0 when nothing matches. Best-effort, not a guaranteed parser for every layout.

One combined, agent-readable summary of a page — title, short summary, links, prices and contacts — assembled from a SINGLE fetch (the most economical of the five). entities is [] in v1 (no entity recognition yet).

Fetch a URL, strip noise (script/style/nav/footer/cookie banners) and return the page title plus markdown-ish text (headings as #..######, paragraphs/list-items as lines). Not a full HTML-to-MD conversion.

Full rendered Wikipedia article as clean HTML (Parsoid). Append the page title to the path, e.g. /api/rest_v1/page/html/Bitcoin.

Concise summary of a Wikipedia article: title, description, plain-text extract and thumbnail. Append the page title to the path, e.g. /api/rest_v1/page/summary/Bitcoin.

Full-text search across Wikipedia. Returns matching pages with title, description and a match excerpt.