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_api_sports_football_get_standings

Retrieve the league table standings and team rankings for a specific football league and season using API Sports Football.

ae_api_sports_football_get_injuries

Check football player injury reports by team, league, or date using API-Sports.

ae_news_get_top_headlines

Get live top and breaking News API headlines by country, category, source, or keyword. Choose at least one of these filters.

ae_law_get_list

按标题、正文用词、发文字号和筛选项,从北大法宝法规库检索法规列表,返回一页可直接引用的法规题录、中文引注和法宝链接,不含法规正文。

ae_bilibili_fetch_video_playurl

Retrieve playback stream data for a video. Supply both the BV identifier (`bv_id`) and the video's content ID (`cid`); both are required. The response contains playback data, whose exact fields and available streams depend on the returned result.

ae_sorftime_patent_request

Look up a patent by its publication number. Provide the required publication_no string, such as CN308683395S; a number returned by patent_search_from_image or patent_search_from_keyword can be used. The provider describes the information available as patent type, issuing authority, inventors, applicants, LOC/IPC/CPC/GBC classification codes, legal status, application date, publication date, estimated expiry date, patent images, and a PDF download link. Actual content depends on the provider response; a structured output schema is not specified. Estimated expiry dates are not definitive legal conclusions.

ae_alphaxiv_discover_papers

Discovers and ranks multiple candidate papers for a research topic. Use this for literature discovery, related work, broad topical coverage, or what is newest on a topic. Do not use it to locate one known paper — name that paper to a PDF tool directly. You get 2 searches per message, so cover every facet of the request in one broad call rather than spending them on several narrow ones. Provide request_body with an English question, focused keywords drawn from the user's request or previous tool results, and a difficulty estimate from 1 to 10 for retrieval effort. Translate non-English keyword terms into English, but preserve acronyms and names rather than guessing their expansions. Higher difficulty takes longer and enables multi-round searches. Optionally set prioritize to default, recency, historical, or popular to emphasize recent-year work, newest matches, foundational work, or community votes, respectively, after topical relevance. Use published_after and published_before (YYYY-MM-DD, inclusive) only when an explicit publication-date boundary is needed; to favor newer work without excluding older papers, use recency instead.

ae_openweathermap_get_weather_overview

Get a human-readable OpenWeatherMap summary for today or tomorrow at a location, with standard, metric, or imperial units.

ae_firecrawl_check_crawl_status

Check the current status of an existing Firecrawl crawl. **Parameter:** `id` — the crawl job ID. **Returns:** A snapshot that may contain the crawl ID and starting URL, status (`scraping`, `completed`, `failed`, or `cancelled`), completed and total page counts, result data, pagination URL, expiry time, and credits used. Optional success, error, or warning details may also be present. Result data follows the upstream structure, and response fields may be absent. This operation only checks an existing crawl; it does not start or resume one. A crawl with status `scraping` may still be in progress. Page counts are not credit counts.

ae_qweather_time_machine_weather

Retrieve historical weather data for a specific location and date within the last 10 days.

ae_tavily_crawl

从起始URL探索并抽取多页内容,支持相关指令、分块、深度、数量、域名及路径筛选。通过Tavily Crawl API同步返回各页面的URL和抽取正文,正文可选择Markdown或纯文本格式;不是仅返回链接的站点映射。探索范围受深度、广度、页面数量和筛选条件限制。费用包含发现链接和正文抽取的实际用量。

ae_dataforseo_llm_mentions_multi_target_metrics

Get aggregated LLM mention metrics for keywords or domains on ChatGPT or Google using DataForSEO.

ae_dataforseo_llm_mentions_top_domains

Identify the top domains mentioned by AI models like ChatGPT or Google for specific topics using DataForSEO.

ae_dataforseo_content_analysis_summary

Get a summary of citation data and sentiment analysis for a keyword using DataForSEO.

ae_api_sports_football_get_fixture_events

Retrieve a timeline of key events like goals, cards, and substitutions for a football match using API-Sports.

ae_law_list_versions

列出一部法规(含司法解释)自己的历次版本,每版给出公布日期、施行日期、被下一版取代的日期和法宝正文链接。不含配套的司法解释、下位法、草案。