18 Services from agent-search.centorprat.workers.dev

Searches and merges academic papers across Google Scholar, arXiv, Crossref, OpenAlex, and Semantic Scholar in a single call, returning unified metadata with open-access PDF links.

Performs a web search and returns the top 1-5 pages as clean markdown with title, author, date, and a prompt-injection safety verdict, plus remaining search results.

Performs comprehensive multi-angle web research by answering a query plus up to 3 sub-questions, reading up to 16 full pages, and optionally including Google Scholar papers or news — returning only extractive quoted passages, no LLM generation.

Returns Google search results as seen by a user in a specific country, language, and city, including local map pack businesses, top stories, and per-result domain metadata.

Answers a natural language question using live web data, returning quoted passages with source URLs, a confidence level, and related questions — no LLM hallucination.

Polls web or news search results for a query and returns only new (unseen) results since the last call, using a watchId to track state.

Search GitHub repositories and npm packages for a coding task, returning results ranked by stars and relevance with metadata like last push date and links.

Searches Google News and Google News RSS, merges and clusters results by story, returning one row per story with the best outlet, coverage count, and clean links — ranked by authority, recency, and breadth.

Performs a single web search query with Google-quality results re-ranked for authority, optionally merged with academic papers, GitHub repos, and news, returning ranked results with domain authority and type metadata.

Runs up to 10 parallel web search queries in a single API call at a discounted per-query rate, returning authority-ranked results for each.

Fetches full text and highlights from up to 10 URLs in Exa /contents-compatible format, returning clean markdown with prompt-injection detection

Drop-in replacement for Exa /search that returns Google-quality authority-ranked web results with page text and highlights included, at lower cost than Exa.

Scrapes a public URL and returns markdown, links, and raw HTML with metadata and a prompt-injection verdict, using a Firecrawl v1-compatible request/response format.

Drop-in Firecrawl v1 /search replacement that returns markdown-scraped web results with prompt-injection verdicts at a lower price per call

Fetches full Google search results pages including organic results, answer boxes, knowledge graph, People Also Ask, related searches, top stories, local pack, domain authority, and page summaries for any country/language/city.

Compares Google search results for a single query across 2–4 countries or cities side by side, showing top-10 results per location, shared URLs, unique URLs, position tables, and overlap metrics.

Drop-in Tavily API-compatible web search endpoint returning ranked results with optional extractive answers and raw page content, at a lower price than Tavily.

Searches the web, reads up to 8 full pages, and extracts the 15 most relevant passages with sources to answer a research question in a single API call.