Sort

AgentEarth Tool Catalog

InformationRetrieval

356Tools
14tags
35Providers

Connect once to Google, Bing, Tavily, Exa, Firecrawl and more for web search, full-site crawling and structured extraction at lower cost.

  1. High-frequency retrieval and complex crawling are optimized for stability to reduce mid-task failures.
  2. Start search and crawling in one place for deep research, competitor monitoring, sentiment tracking and information collection.

Tool List

356 tools

ae_dataforseo_serp_youtube_organic_live_advanced

Retrieve live organic YouTube search results for a specific keyword, location, and language using DataForSEO.

ae_brightdata_scrape_as_markdown

Fetch a single web page through Bright Data for reading, summarization, or content extraction. Provide the required `url` as a page URL. The optional `format` parameter accepts `markdown` (default), `text`, `html`, or `ld_json`. The documented result is JSON containing `url`, `title`, `format`, and `content`. Markdown provides readable page content; text provides plain text without links or headings; HTML provides raw markup for inspection or later extraction with CSS selectors; LD-JSON provides schema.org data present on the page, such as price, rating, or author. The content is returned in one format. If the page has no data in the requested format, the tool returns Markdown instead and includes a note. The tool does not render JavaScript. Requests that take longer than 45 seconds time out.

ae_you_get_search

Search the web for real-time results and news articles.

ae_openweathermap_get_day_summary

Retrieve aggregated OpenWeatherMap weather data for a specific date and location, covering dates from January 2, 1979 through approximately 1.5 years ahead.

ae_serper_scholar

Search for academic papers, citations, and scholarly articles.

ae_chanmama_extract_video_copywriting

Extract spoken copy from one video. Provide exactly one of query.video_url or query.video_id. Videos longer than 10 minutes may fail extraction; prefer videos within 10 minutes.

ae_serper_patents

Search Google Patents for granted patents and pending applications to find inventors, assignees, and technical details.

ae_bid_search_company

Search company lists by company name, abbreviation, or alias, and filter by province or city. Returns matching enterprises with IDs, full names, locations, and historical bidding/winning counts.

ae_exa_web_search_exa

Search the web for relevant pages, companies, people, or research papers.

ae_tavily_extract

从已知URL抽取正文,支持相关问题、分块数量、深度、图片和输出格式。兼容单个URL或URL数组。部分网页可能抽取失败,需检查failed_results;按实际用量结算。通过 Tavily Extract API 同步返回抽取结果:results 包含成功页面的 URL 和 raw_content,正文格式可选 Markdown 或纯文本;提供 query 时,raw_content 返回相关片段而非完整抽取内容。可按选项附带图片链接、站点图标和估计的发布时间或更新时间。failed_results 列出失败 URL 及原因;即使请求成功,results 也可能为空。

ae_firecrawl_research_read_paper

Read the passages in one specified paper that are most relevant to your question, for example to verify a technique or benchmark result before including or rejecting the paper. Inputs: paperId (required nonempty canonical paperId or primaryId, such as arxiv:1706.03762, pmcid:PMC12530322, pmid:40953549, or doi:10.1016/j.neunet.2025.108095); question (required nonempty string); and k (optional integer 1–50, default 4) for the number of passages to return. No additional inputs are accepted. The result contains a passages array whose items may include text as a string or null, plus optional agent_hints guidance strings. If no full text is indexed, passages is empty; the service may also provide an unavailability notice. This retrieves relevant excerpts from one paper, not the complete document or a search across papers. Missing passages do not establish that a claim is false. Results are returned directly by the configured synchronous mapping, with no asynchronous task submission, status polling, or separate result-retrieval step.

ae_bravesearch_news_search

Find real-time news articles from trusted sources worldwide. Filter results by freshness (e.g., last 24 hours), country, and language to track breaking news or monitor media coverage.

ae_brightdata_scrape_batch

Fetch 1–5 web pages per batch with Bright Data. Provide the page URLs in the required urls array and optionally choose one format for the batch: markdown (default), text for plain text without links or headings, html for raw HTML, or ld_json for available schema.org data such as price, rating, or author. Results are returned as a JSON array in the same order as the input URLs. Each successful item contains url, title, format, and content; each failed item contains url and error. If a page has no data in the chosen format, its result falls back to Markdown with a note. The tool does not render JavaScript, and pages taking longer than 35 seconds time out.

ae_linkup_search

Search the web for factual answers, sources, or structured data to ground AI responses.

ae_linkup_fetch

Extract clean text, images, or raw HTML from a specific webpage URL.

ae_dataforseo_serp_google_organic_live_advanced

Get live Google organic search results through DataForSEO for a keyword and geographic location. Put task parameters in the request_body array according to this interface schema.