Tool Name | Platform/Category | Description |
---|---|---|
Apollo Company Enrichment | Business Data | Search for company details in Apollo database |
DuckDuckGo Search | Search Engine | Basic web search using DuckDuckGo |
Tavily Search | Search Engine | Advanced semantic search with AI-optimized results |
LinkedIn Profile Scraper | Social Media | Extracts detailed information from LinkedIn profiles |
Twitter Profile Scraper | Social Media | Collects data from Twitter/X user profiles |
Twitter Search Scraper | Social Media | Gathers tweets based on search terms |
Website Scraper | Web | Extracts text content from web pages |
Video Transcript Extractor | Multimedia | Retrieves transcripts from video/audio content |
Wikipedia Search | Knowledge Base | Searches and retrieves Wikipedia article content |
apollo_organization_enrichment
Arguments:
Name | Required | Type | Description |
---|---|---|---|
domain | Required | string | Company domain to search for |
duckduckgo-search
Arguments:
Name | Required | Type | Description |
---|---|---|---|
maxResults | Optional (default: 5) | number | Maximum number of search results to return |
tavily-search
Arguments:
Name | Required | Type | Description |
---|---|---|---|
maxResults | Optional (default: 5) | number | Maximum number of search results to return |
linkedin_scrape_profiles_by_urls
Arguments:
Name | Required | Type | Description |
---|---|---|---|
profileUrls | Required | string[] | Array of LinkedIn profile URLs to scrape |
twitter_scrape_by_handles
Arguments:
Name | Required | Type | Description |
---|---|---|---|
twitterHandles | Required | string[] | Array of Twitter handles to scrape |
start | Optional (default: ”) | string | Start date in YYYY-MM-DD format |
end | Optional (default: ”) | string | End date in YYYY-MM-DD format |
sort | Optional (default: ‘Top’) | enum: [‘Latest’, ‘Top’] | Sort order of tweets |
maxItems | Optional (default: ‘10’) | enum: [‘5’, ‘10’, ‘25’, ‘50’, ‘100’] | Maximum number of items to return |
twitter_scrape_by_search_terms
Arguments:
Name | Required | Type | Description |
---|---|---|---|
searchTerms | Required | string[] | Array of search terms |
start | Optional (default: ”) | string | Start date in YYYY-MM-DD format |
end | Optional (default: ”) | string | End date in YYYY-MM-DD format |
sort | Optional (default: ‘Top’) | enum: [‘Latest’, ‘Top’] | Sort order of tweets |
maxItems | Optional (default: ‘10’) | enum: [‘5’, ‘10’, ‘25’, ‘50’, ‘100’] | Maximum number of items to return |
scrape_web_text
Arguments:
Name | Required | Type | Description |
---|---|---|---|
url | Required | string | URL of the webpage to scrape |
video_transcript
Arguments:
Name | Required | Type | Description |
---|---|---|---|
video_url | Required | string | URL of the video/audio content |
language | Optional | string | Language code for the transcript (e.g., ‘en’, ‘ru’) |
wikipedia-query-run
Arguments:
Name | Required | Type | Description |
---|---|---|---|
topKResults | Optional (default: 3) | number | Number of top results to return |
maxDocContentLength | Optional (default: 4000) | number | Maximum content length per document |