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_brightdata_search_engine

Search Bing or Google through Bright Data for current information, news, and source links. Provide the required query string. Optionally set engine to bing or google (default bing), page to a nonnegative integer starting at 0 (default 0), and country to a two-letter country code such as us or de. The optional time_range accepts hour, day, week, month, year, or any and defaults to any; Bing supports only day, week, year, and any. Returns JSON containing organic search results with links, titles, and descriptions, with 10 results per page. To read a result's full page content, retrieve its linked page separately.

ae_serpapi_search

Search Google and other engines for web results, news, images, shopping products, and local business listings.

ae_github_repos_get_content

View or download files, directories, or documentation (like READMEs) from a GitHub repository without cloning it.

ae_bravesearch_image_search

Search images using Brave Search with query, locale, pagination, freshness, and SafeSearch controls. Use this to discover relevant image results, thumbnails, source pages, and visual content from across the web. For image search, safesearch supports only off or strict; moderate is not supported. Omit safesearch to use the provider's default; this tool does not set a default value.

ae_tushare_major_news

Get long-form news reports from major news sites through Tushare, with more than eight years of history. Filter by publication time or source, and optionally include full article content.

ae_openalex_listworks

Search OpenAlex for scholarly works, including articles, books, and datasets, with filters, sorting, and grouping.

ae_dataforseo_backlinks_bulk_spam_score

Check DataForSEO spam scores for multiple domains or pages to assess backlink quality and risk.

ae_bid_get_detail

【唯一的单条标讯获取方式】根据标讯标识获取该标讯的完整正文和附件内容。 这是系统中获取单个标讯详细信息的唯一途径,必须通过以下两种方式之一定位标讯: 1. 提供 uniq_key(公告唯一标识) 2. 提供 bid_id(标讯ID): - 只提供 bid_id:bid_id >= 520000000 时优先尝试 type=1(招标),否则优先尝试 type=2(中标),未命中时自动回退另一类型 - 同时提供 bid_id 和 bid_type:直接查询指定类型(1/招标/招标公告 或 2/中标/中标公告,支持数字或文本) ※ bid_id 支持直接传入知了标讯链接,系统自动解析: https://www.zhiliaobiaoxun.com/content/{bid_id}/b{bid_type} 【批量获取】bid_id 也可传入整型数组(如 [123, 456])一次获取多条标讯: - bid_type 仍只能传一个值,数组内所有 bid_id 共用该类型;未传 bid_type 时按上述阈值分组批量查询并自动回退 - 此时返回 {total, items}(items 为详情对象数组,按传入顺序排列),查不到的 bid_id 自动跳过 - 仅适用于 bid_id 数组场景;传单个 bid_id / uniq_key / 链接时返回单条详情对象(与原有行为一致) 返回内容包括: - 标讯基本信息(标题、时间、金额、地区、招标方、中标方、标的物等) - source:公告正文(HTML格式) - source_ext:附件正文内容 - attachment_urls:从正文中提取的附件链接列表(bailian-ai.com、zhiliaobiaoxun.com、bid.snapshot.qudaobao.com.cn 域名) - source_url:公告原文链接(来源网站的原始页面地址,缺失时为空字符串) - has_source/has_attachment/has_attach_file:正文/附件是否存在的标记 - 联系人字段:caller_person/caller_contact(招标公司联系人/联系电话)、agency_person/agency_contact(招标代理公司联系人/联系电话)、 winner_person/winner_contact(中标公司联系人/联系电话)。联系人姓名已脱敏,仅保留姓氏。 适用场景:查看标讯全文、分析招标文件详情、提取附件中的技术参数等。 注意:如果用户只提供了标题,需要先通过 search_bids 搜索找到对应的 bid_id和bid_type,再调用本工具。

ae_openalex_getwork

Retrieve detailed metadata for a specific scholarly work using its OpenAlex ID, DOI, PMID, or other external identifiers.

ae_brightdata_search_engine_batch

Run 1–5 Bing searches at once. Returns a JSON array in input order: query, engine, and result (organic link, title, description) or error. Searches not done within 45 s return a timeout error. Each query supports country, results page, and time-range settings; Bing time ranges are day, week, year, and any. Google batch search is currently unavailable. For Google, use ae_brightdata_search_engine with engine=google, one query per call; do not silently change a Google request to Bing.

ae_dataforseo_labs_google_related_keywords

Generate related keyword ideas from Google's "searches related to" section using DataForSEO. Includes search volume trends, CPC, and competition metrics.

ae_firecrawl_research_inspect_paper

Fetch canonical metadata for one paper by supplying its required paperId. The identifier can be a canonical paperId or primaryId, for example an arXiv, PMC, PMID, or DOI identifier. The response includes a paper record with available identifiers, title, authors, abstract, categories, and creation and update dates; paper may be absent if the requested paper is not found. Optional agent_hints may also be returned. This performs a direct lookup and has no asynchronous task lifecycle.

ae_chanmama_video_storyboard

Break down a single video into storyboard segments with segment timing, video URLs, and speech text. In query, provide a Chanmama video ID (video_id), a supported video link (video_url), or both. Supported links include Chanmama, Douyin, and creative-platform share links. Prefer videos shorter than 5 minutes. If a video is reported as too long, use a shorter clip that the tool can recognize.

ae_dumplingai_search_youtube

Search for YouTube videos, shorts, or channels by keyword using DumplingAI.

ae_serper_autocomplete

Get Google search autocomplete suggestions for a given text prefix to help refine queries or implement type-ahead search.