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_imdb_get_title_recommendations

Find titles similar to a known title for recommendations or catalog curation. Supply the required id as an IMDb title identifier in tt<digits> format. Optionally set languageCountry to en_US, fr_CA, fr_FR, de_DE, hi_IN, it_IT, pt_BR, es_ES, es_US, or es_MX; the default is en_US. The response contains the recommendation payload in data, together with code, message, and recordTime. The detailed fields within data are not specified, so particular title attributes, result counts, or rankings are not guaranteed.

ae_imdb_get_title_redux_overview

Retrieve a consolidated overview of a title for catalog review or content research. Provide id in the format tt followed by digits; optionally choose a supported languageCountry preference (default: en_US). This looks up a known ID rather than searching by title name. The response includes the overview payload in data, plus code, message, and recordTime. Specific overview fields are not guaranteed by the documented response schema.

ae_imdb_get_title_release_expectation

Look up release-expectation information for a title using its ID (tt followed by digits). Optionally choose a supported language and country/region preference with languageCountry; the default is en_US. The response provides the available release-expectation data and a result code, message, and record time. The data fields are not fixed by the response specification, and expectations should not be treated as confirmed release dates. Useful for researching a title’s release context and supporting release planning.

ae_imdb_get_title_top_cast_and_crew

Look up a title's principal cast and crew using its IMDb title ID (id, formatted as tt followed by digits). Optionally set languageCountry to a supported language and country/region preference; the default is en_US. Useful for researching key talent or enriching title credits. The response includes cast-and-crew data in data plus code, message, and recordTime. The detailed data structure is not specified, and a complete credits list is not guaranteed.

ae_imdb_get_title_user_reviews_summary

Retrieve a title’s user-review summary to help assess audience reception or support title comparisons. Provide the title ID in tt<digits> format. Optionally choose languageCountry from en_US, fr_CA, fr_FR, de_DE, hi_IN, it_IT, pt_BR, es_ES, es_US, or es_MX; it defaults to en_US. The response includes the summary payload in data and code, message, and recordTime metadata. Specific summary fields are not defined, so the result should not be assumed to include individual reviews or ratings.

ae_wechat_official_accounts_search_miniprogram

Search for WeChat mini programs related to a brand, service, topic, or product. Provide the required keyword. Optional pagination inputs are currentPage (starting at 1), offset (0 for the first page), and cookies_buffer (empty for the first page). For later pages of the same search, advance the page number and reuse the offset and opaque pagination state from the previous response when provided. Returns a JSON response with status code, search payload in data, message, and recordTime metadata. The fields within data are not specified, so result details and pagination state depend on the actual response. Searches mini programs rather than official accounts or articles; it does not open or run them.

ae_brightdata_get_scraper_progress

Check the status of an existing Bright Data scraper run using the required snapshot_id string returned by run_scraper. Returns the run status: starting, running, ready, failed, or canceled. When the status is ready, use get_scraper_results to retrieve the scraped data.

ae_brightdata_get_scraper_results

Retrieve records collected by an existing Bright Data scraper run. Provide the required snapshot_id string returned by run_scraper. The tool returns the run's records once they are ready; otherwise, it returns status "running", and you can check again later with the same snapshot_id. The returned record fields and response structure depend on Bright Data's response; no output schema is specified.

ae_dataforseo_serp_bing_organic_live_advanced

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

ae_alphaxiv_api_get_paper

Get paper details and cited-by count by arXiv ID, optionally with a version suffix.

ae_alphaxiv_api_get_paper_references

Get parsed references by arXiv ID, including original citation text, page and matched DOI or arXiv ID when available.

ae_alphaxiv_api_get_paper_metadata

Get authors, abstract, version and links by supplying a bare arXiv ID as upid.

ae_alphaxiv_find_researchers

Find researchers by research topic or name, current organization or role, citation range, position history, and verified coauthorship. Use this tool first for organization rosters, who has left an organization, career moves, and what researchers are doing now. Results include researcher handles in the form [SLUG=...]. Supply your search criteria in request_body. For subject searches, prefer topic and describe one focused concept using the terminology of papers in that field. Use affiliation and role for current positions, or position for historical roles and dates; all conditions within position apply to the same LinkedIn experience entry. Combine current and historical filters to investigate transitions. Use page and limit to browse further matches. For collaborator, advising, or lab-membership questions, set relationship.kind to coauthored_with and provide the anchor researcher's full name or exact [SLUG=...] handle in relationship.researcher. Relationship results summarize evidence from linked public alphaXiv papers: shared publications, their share of each candidate's output, lead-author counts on papers where the anchor is last author, collaboration years, and current position. Use require_position_overlap with position.affiliation to narrow candidates to people with overlapping time at that organization. If the anchor has no dated position there, the results report that limitation and rely on coauthorship. These records help assess possible relationships; an exact advising or lab title needs a source that explicitly states it. Do not use this tool only to resolve a name for another profile or relationship call; pass the name directly to that call.