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_serper_search

Search the web for real-time results, including news, images, videos, local places, and academic papers.

ae_firecrawl_scrape

Scrape one specified URL with Firecrawl and return content in the formats you choose. The required `url` is the page to retrieve. `formats` can request markdown, HTML, raw HTML, screenshots, links, summary, change tracking, branding, JSON, a targeted query, or audio. For structured fields, use `formats: ["json"]` with `jsonOptions` containing an extraction prompt and, if needed, a JSON schema. For a targeted answer, use the query format and provide `queryOptions.prompt` and `queryOptions.mode` (`directQuote` or `freeform`). Optional settings include `waitFor` for JavaScript-rendered pages; `onlyMainContent`, `includeTags`, and `excludeTags` for content selection; `proxy`, `mobile`, and `location` for page loading; `parsers` and `pdfOptions` for PDF processing; and `screenshotOptions` for screenshot output. `redactPII`, `removeBase64Images`, `zeroDataRetention`, and `skipTlsVerification` configure privacy or request handling. `maxAge` controls acceptable cache age; set it to `0` to require a fresh scrape. With `lockdown: true`, retrieval uses only the existing cache or index and fails on a cache miss. The operation returns the selected extracted content and page metadata in a direct response; it is not an asynchronous job. Firecrawl may reuse cached content, so a successful result does not necessarily represent the page's current live state. This tool handles one known URL; use crawl for multiple pages or map/search to discover URLs.

ae_dataforseo_labs_google_ranked_keywords

‌ This endpoint will provide you with the list of keywords that any domain, subdomain, or webpage is ranking for. You will also get SERP elements related to the keyword position, as well as monthly searches and other data relevant to the returned keywords. The public input is a tasks array containing exactly one task per call. The task's optional filters field accepts official condition arrays, not a list of objects. A single condition can be ["ranked_serp_element.serp_item.rank_group","<=",10]. Multiple conditions can be combined as [["ranked_serp_element.serp_item.rank_group","<=",10],"and",["ranked_serp_element.serp_item.type","<>","paid"]], with nested "and"/"or" expressions supported. Matching keywords are not guaranteed; results depend on available data and the specified conditions. When using this tool, each order_by rule must be a fully qualified response field path, for example keyword_data.keyword_info.search_volume,desc or ranked_serp_element.serp_item.rank_group,asc; bare field names such as search_volume or rank_absolute are not accepted. You can set up to three sorting rules, separating the field path from asc/desc with a comma and using a separate array item for each additional rule. The default is ranked_serp_element.serp_item.rank_group ascending.

ae_github_search_repos

Search GitHub repositories by keywords, programming language, topic tags, popularity, or recent activity.

ae_firecrawl_search

Search web, news, or image sources and return ranked results grouped by source. Provide a non-empty `query`; optionally set `sources` (web, images, or news), `limit` (1–100), time filter `tbs`, `filter`, `location`, `categories` (`github`, `research`, `pdf`, or `developer`), `enterprise`, and `highlights`. Use `includeDomains` to restrict results or `excludeDomains` to exclude hostnames; these fields are mutually exclusive. Search query operators include quoted phrases, `-term`, `site:host`, `inurl:term`, and `intitle:term`. You can provide `scrapeOptions` to extract selected content from returned pages in the same call, with options for formats, parsers, PDF handling, page content selection, screenshots, structured extraction, and related settings. Such fetches ignore `maxAge`; use the dedicated scrape operation when you need a live fetch. Search results normally contain a title, URL, and description, not the full page. Developer-category results are returned in `data.web` with `category: "developer"`; research-category web results are restricted to research-affiliated sites and include snippets. The synchronous response may include `success`, source-grouped `data` (such as `web`, `news`, `images`, or `alexandria`), `id` for optional search feedback, `creditsUsed`, `warning`, `error`, and follow-up/tool metadata such as `nextTool`, `feedbackTool`, `tools`, `agent_hints`, or `conversationId`. `includeDomains` and `excludeDomains` must not both be supplied. This operation does not provide asynchronous job submission or polling.

ae_dumplingai_scrape_webpage

Extract text or HTML content from a specific webpage using DumplingAI.

ae_serper_images

Search for images using Google Images to find visual assets, photos, and thumbnails for your projects.

ae_serper_news

Find recent news articles and headlines from Google News. Track current events, breaking news, and media coverage for specific topics or brands.

ae_dataforseo_labs_google_keyword_overview

Get Google search metrics like volume, CPC, and competition for specific keywords using DataForSEO.

ae_bid_search

Search tender and bidding announcements across multiple dimensions such as keywords, regions, dates, amounts, and organizations.

ae_dataforseo_labs_google_domain_rank_overview

Get an overview of a domain's organic and paid search performance using DataForSEO. View ranking distribution and estimated monthly traffic volumes.

ae_bravesearch_web_search

Search the web for pages, local businesses, and real-time data like weather, stocks, or sports scores. Filter by date, location, and language to find relevant information.

ae_bid_get_company_registry

Query official corporate registration and business registry information by company full name or common abbreviation, including unified social credit code, legal representative, registered capital, operating status, establishment date, and business scope.

ae_firecrawl_research_search_papers

Search for research papers across indexed areas including AI/ML, computer science, mathematics, physics, biomedical and life sciences, and clinical literature. Provide a natural-language research topic or question as `query`. You may request `k` ranked papers (1–500; default 40), filter by `authors` (all supplied case-insensitive author substrings must match) or `categories` (all supplied values must match), and set inclusive `from` and `to` bounds for created or updated dates using `YYYY-MM-DD`. The synchronous response contains a ranked `results` array; paper records may include `paperId`, `primaryId`, source `ids`, title, authors, abstract, categories, and created/update dates. Optional `agent_hints` may be included. Try several distinct formulations of a topic for broader recall. This is a search operation, not an asynchronous task workflow.

ae_tavily_search

搜索网页、新闻及财经信息,支持时间、语言、域名、相关片段数、正文格式和答案选项。返回标题、网址、相关片段和评分;所选类型可附带发布时间。费用按本次实际供应商积分计算。