Integrations / Search
Tavily
Search the web with Tavily for answers and clean page content in one call, extract pages by URL, and map or crawl a site.
Tools
tavily.search
Search the web. Returns up to 20 results with title, URL, a relevant excerpt and a relevance score, plus a short answer if asked. advanced depth costs 2 credits instead of 1.
tavily.extract
Get the content of up to 20 pages by URL as markdown or text. With a query, returns only the excerpts of each page most relevant to it. Pages that couldn't be read come back in failed with the reason.
tavily.map
List the URLs of a site by following its links from a starting page, without reading their content. Good for finding the pages worth extracting.
tavily.crawl
Follow a site's links from a starting page and return each page's content as markdown. Keep limit small: the crawl has to finish within the request, so it stops after about 15 seconds.
tavily.api_get
Send a GET request to any Tavily API path under https://api.tavily.com and return the response. For endpoints the named tools don't cover.
tavily.api_request writes
Send a POST, PUT, PATCH or DELETE request to any Tavily API path under https://api.tavily.com.
Tick Allow raw writes on the connection to add api_request, which can send POST, PUT, PATCH and DELETE requests to any Tavily API path.
Connect
- In the Tavily dashboard (app.tavily.com), open the Overview page and copy the API key under API Keys, or click + to create another.
- Paste it (tvly-…) as the connection's API key. Searches, extractions, maps and crawls are billed in credits to that account; verifying reads the key's usage and costs nothing.
Credentials
Turn one person's AI process into the company's.
Murmurator is invite-only. Already invited? Sign in and build something real.