Search & web

Search Japanese corporate disclosures (FSA EDINET): securities reports and shareholding reports.

Search official Japanese government statistics (e-Stat): population, economy, labor, and more.

Search Japanese corporate disclosures (FSA EDINET): securities reports and shareholding reports.

Search official Japanese government statistics (e-Stat): population, economy, labor, and more.

STIL lab at ETS Montreal — knowledge base and paper search via ArXiv and Semantic Scholar.

Semantic search across 5 US government healthcare databases.

Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.

Monitor web pages for changes with AI-powered change detection, diffs, and alerts.

Pay-per-call SEO agent: keyword research, SERP analysis, on-page optimization. x402, USDC on Base.

Help center for SaaS teams. 14-tool MCP server for articles, collections, and search.

Remote MCP server: fetch, search, Python, TTS, memory, image, video.

Used car catalogue in Portugal. Search by make, model, price, mileage, fuel and district.

Parse a User-Agent header into structured data: browser (name/version), rendering engine, operating system, and device type/vendor/model. Deterministic — the same string always parses identically. Use this when an agent needs to uA string → browser, engine, OS and device.

+5 more from AgentTools

ALICE V0 — Web Search: Search the web for any query — returns top 10 results with titles, URLs, and snippets. Powered by DuckDuckGo.

Turn a small website, or one section of it, into clean Markdown: starts from your URL, finds pages from the sitemap or by following links on the same site, obeys robots.txt, and returns up to 10 pages (title, Markdown, address) in one call. Great for docs, blogs and company sites. ?url=https://example.com/docs/&maxPages=10&path=/docs/

+15 more from Aayat AI

Tavily Search - advanced mode

Research brief on any topic in one call: the best papers from ISHOB's open-licence archive, filled with a live search of 250M+ scholarly works, each with authors, year, venue, DOI and citations; abstracts only for openly licensed papers (CC0 / public domain / CC BY / CC BY-SA), metadata and link for the rest; plus a short AI synthesis citing the papers as [n]. Checked before payment: if nothing is found anywhere the answer is a free 404 'not_covered'.

Returns possible Argentine address matches from Georef, preserving source records, URL and reading time. An optional province identifier restricts the request; records outside that province cause rejection. Results do not guarantee a unique or correct match or an exhaustive search.

+1 more from tienda.textokit.store

Extract keywords and keyphrases from a text without AI (RAKE algorithm scoring frequency and degree), in Spanish or English, plus most frequent words. For tagging, indexing and SEO.

+1 more from AI keyword extraction

All links on a page classified as internal or external, with anchor text, nofollow/sponsored, new-tab flags and the most linked external domains. For SEO, crawling and audits.

+1 more from Page links | Vextorium

Who is this company, officially? Global LEI lookup and legal-entity search against GLEIF, the ISO 17442 registry behind KYB, MiFID and EMIR reporting. Verify an LEI's checksum and registration status, or search 2.9M+ entities by name and country to find the right identifier. Flags LAPSED, DUPLICATE and RETIRED registrations that a naive first-hit lookup would wire into a KYB record. Deterministic: no LLM.

ClinicalTrials.gov lookup, deterministic. Answers "what is the status of NCT02142738", "recruiting phase-3 melanoma trials", "Pfizer trial pipeline". Single trial by NCT id (status, phase, sponsor, enrollment, dates, countries) or search by condition/sponsor with phase and status filters. Typed records straight off the official v2 API — no LLM, no key, public domain.

BC Childcare Register: buy one current structured obligation record with original-source citations. Find a relevant ID first with free search at https://getregisters.com/api/v1/agent-search?feed_id=bc-childcare, then buy its agent_offer.url. Current full structured version at purchase; no history or future updates. Licence: https://getregisters.com/agent-licence.html

Searches French companies by name, SIREN, SIRET or optional location criteria and returns structured matching company records.

Fetch an OpenAPI/Swagger spec (JSON or YAML) and summarize it for an agent: title, version, servers, authentication schemes and every endpoint with method, path, summary and required parameters.

+1 more from OpenAPI spec summary for agents

List the URLs of a site's XML sitemap (found via robots.txt if needed, following sitemap indexes and .gz files) with last-modified dates, optionally filtered by text. Discover a site's pages for crawling or monitoring.

+1 more from Sitemap URL extractor

Search scientific papers on arXiv (AI, physics, maths, economics...): title, authors, abstract, categories, dates and PDF link; by relevance or newest, with category filter (cs.AI, cs.CR, q-fin...).

Parse a site's robots.txt: whether a user-agent may crawl a path, which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot...) are blocked, and declared sitemaps. Check before your agent scrapes.

+1 more from robots.txt & AI crawler rules

Extractive summary without AI: picks the most representative sentences (term frequency and position scoring) and returns them in original order, with the reduction percentage. Deterministic and instant.

+1 more from Extractive summary | Vextorium

Validate JSON (with line and column of the error), pretty-print or minify it, describe its structure (depth, keys, value types) and extract a value by path such as data.items[0].price.

+1 more from JSON validator & extractor