Web & Data

Monexus Terminal API — Search 368 episodes of business/finance podcast corpus (FTS5). Params: q (>=3 chars), limit (<=20).

Monexus Terminal API — Full context brief: /api/v1/thread/{id}/context.

ElevenLabs TTS — reference quote

Machine-readable description decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Structured extraction of one web page: title, description, headings, clean main text, markdown, links and images.

Reloadpi — Topup purchase schema. Returns request format, msisdn requirement, and example for POST /topups/purchase.

Reloadpi — Order status and refund schema. Returns the fulfillment state machine, polling URL, and refund endpoint for any paid order.

Live economy: treasury, agent count, total USDC, AGWC supply, Gini.

Returns up to 168 hours of historical signal snapshots with timestamps and per-symbol scores — use it to backtest, chart signal drift, or build training data.

FDA drug labels (package inserts) by brand or generic name from openFDA, newest label first: brand, generic name, manufacturer, indications and usage, warnings, label date. ?q=ibuprofen; 5 labels by default, up to 25 with &limit=. Answers are cached for up to 24 hours. Not medical advice.

NVD (National Vulnerability Database) CVE record by id, or search by keyword in recent CVEs: description, severity and CVSS base score, status, published and last-modified dates, and whether it is on CISA's Known Exploited list. Cached; records refreshed within about 48 hours.

npm package card from the official registry: latest or a given version, description, license, maintainers, keywords, repository, dependencies count and publish dates. Required: name; optional: version. Cached.

FRED (Federal Reserve Bank of St. Louis) series observations by series id, e.g. GDP, UNRATE, CPIAUCSL: dates and values with the series title, units and frequency.

Search Canada's federal open data portal (open.canada.ca) by keyword, or fetch one dataset by id: English and French titles, publishing organization, last modified date, number of resources and the total match count.

Search Germany's open data portal GovData by keyword, or fetch one dataset by id: title, publishing organization, last modified date, resource count and total match count.

US court opinion search on CourtListener (Free Law Project): case name, court, date filed, docket number and the opinion link. Short queries match as a phrase (?q=fair use), longer ones need every word. Cached; a query not yet cached is fetched live.

Live state of the GBLIN rebalancing auction on Base: open or not, current premium over the oracle price (rises to the cap over one ramp), and side and gap per basket row. Bidding is trading with the vault toward its target weights; the premium is the reward and nothing is paid out of the vault.

Checks one URL without downloading the page: HTTP status, the full redirect chain hop by hop with the code of each, the final URL, whether it ends on HTTPS, content type and size, and the security headers the server sends. Built for going through a list of links one at a time. No API key, no account.

Everything DNS says about one domain in a single call: whether it is registered, its A and AAAA addresses, nameservers, MX servers, SPF and DMARC, DNSSEC, and whether it looks parked. Built for going through a list of domains one at a time. Live DNS, no API key, no account.

Structured web extract for AI agents: fetch any public URL, return schema-constrained JSON for SaaS pricing, contacts, team, product, FAQ, or task-shaped fields. Confidence scores and source snippets. No API key — pay-per-call x402 USDC on Base ($0.02). Better than raw crawl markdown for agent tools.

Download MJCF XML for the generated scene

Read any public web page as clean Markdown: main-content extraction (navigation, footers, scripts and hidden elements removed), headings, lists, tables, code blocks, links (absolute, deduplicated), images, plus title, description, canonical URL, language, author and publish date, and a content hash + fetch time as evidence. JSON and plain-text URLs are returned as-is. No JavaScript rendering. $0.001 per page.

Current weather and a 3-day forecast for any city or lat/lon - temperature, humidity, wind, conditions. No account, no API key. Try GET /weather/sample.

Checks one IPv4 address against nine public DNS blocklists at once — SpamCop, UCEPROTECT, PSBL, Barracuda, DroneBL and four more — and returns each list's raw return code plus the reason text the list itself publishes, not a score. Every list is re-checked on each call with its RFC 5782 test entry, so a dead list or one that refuses queries comes back as unavailable instead of reading as clean. Includes the delisting URL for each hit.