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_exa_web_fetch_exa

Retrieve full text, summaries, and metadata from a list of specific URLs.

ae_perplexity_search

Search the web to retrieve ranked results, including titles, URLs, and snippets, without AI-generated summaries.

ae_tushare_news

Get short news alerts from mainstream news sites through Tushare for a specified source and time range, with more than six years of history.

ae_you_post_contents

Extract clean text or Markdown content from specific webpages.

ae_tushare_cctv_news

Get the text transcript of CCTV's Xinwen Lianbo broadcast for a selected date. Coverage starts in 2017.

ae_bid_query_advanced

An advanced search tool for government and enterprise procurement and bidding notices. It supports rich filtering combinations, such as keyword match modes (product, caller, winner, agency, full text), keyword groups with AND/OR logic, procurement stages (intent, pre-bid, tender, winner, contract, acceptance, invalidation), absolute date ranges (YYYY-MM-DD), project budget/amount ranges (in 10k RMB), regions, and incremental data ingestion timestamps.

ae_serper_videos

Search for videos on Google, including YouTube results with titles, channels, and durations.

ae_openweathermap_get_timemachine

Retrieve OpenWeatherMap weather for a specific timestamp and location, from January 1, 1979 through four days ahead. Use a Unix timestamp in seconds and choose standard, metric, or imperial units.

ae_zhihu_scholar_search

Search for academic papers by keyword. Provide the required `keyword`; optionally use `offset` (default `0`) and `limit` (default `25`) to control pagination. An optional `request_body` object can contain filter criteria such as `indexed_by`, `classification`, and `advanced_filter` (whose default is `keywords,title,authors,abstract`). The response contains the search payload in `data` and may include status, request parameters, timing, and other response metadata. The fields and contents of the search payload depend on the results returned.

ae_dumplingai_search_news

Search global news articles and headlines by topic, date, or region using DumplingAI.

ae_dataforseo_labs_google_keyword_ideas

Generate relevant keyword ideas with search volume, CPC, and competition data using DataForSEO to expand your SEO or PPC strategy.

ae_linkup_get_research

Check the status and retrieve results of a Linkup research task using its task ID.

ae_dataforseo_backlinks_bulk_ranks

Get backlink authority scores for multiple domains or pages using DataForSEO. Returns a rank from 0 to 1,000 based on the number of referring domains.

ae_dataforseo_labs_google_historical_serps

View historical Google search results, rankings, and featured snippets for a keyword over time using DataForSEO.

ae_firecrawl_developer_search

Search an index built for coding agents when you have a question about code behavior, a library or framework, an API contract, an error message, or a known bug. The indexed sources include repositories, GitHub issues, merged pull requests, repository READMEs, and curated documentation sites. Results are ranked and include an ID, source type, URL, title, and matching passages in markdown. The required query describes what you want to find. Optionally provide k (an integer from 1 to 100) to control the number of results. Set skills to "only" to restrict the search to agent-skill files; otherwise, the search is not limited to that subset. Results are returned directly; this operation does not expose an asynchronous job or polling parameters.