LabscoMCP early access ↗
TavilyMCP SERVER · OFFICIAL PROJECT

Tavily MCP

Web search built for agents, with domain filtering, plus page extraction, site crawling and mapping, and multi-source research.

by Tavily ↗Web Search Engines✓ Official

LABSCO SUMMARY

Domain restriction is the filter that turns a search tool into a research tool.

Most agent searches fail not because the answer is missing but because the top results are content marketing. Pinning a search to the domains you trust — a vendor's docs, a regulator, a handful of publications — changes what comes back more than any prompt tuning will. One caution: passing the key as a URL parameter puts a credential into config files and shell history; prefer the header or OAuth where your client supports it.

What it is

Tavily's own hosted endpoint for agent web research. Their search is built for retrieval by models rather than for human browsing, which shows in the filtering.

What you get

  • tavily_search — live web search with filters, including restricting results to the domains you name
  • tavily_extract — the content of one or more pages, as markdown or plain text
  • tavily_crawl — crawl a site from a starting URL, with depth, breadth and plain-language instructions for what to collect
  • tavily_map — list the URLs on a site, starting from a base URL
  • tavily_research — research a question across several sources and return a detailed answer, up to 20 requests a minute

Requirements

  • An API key from Tavily's console, or OAuth sign-in. Either one runs every tool.
  • With no key, connect with the keyless header instead: tavily_search and tavily_extract run, free and rate-limited; tavily_crawl, tavily_map and tavily_research need a key or sign-in.

Setup effort

Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen