# Tavily — MCP Server

> Search, extract and crawl the web for AI research agents via Tavily.

**Source:** https://mcpplaygroundonline.com/mcp-servers/tavily  
**Transport:** stdio  
**Requires auth:** Yes

---

## What it does

The Tavily MCP server wraps the Tavily API as four MCP tools. Models can run a real-time web search tuned for LLM consumption, extract the main content from one or more URLs as clean markdown, crawl a site by following links to a set depth, and map a site's URL structure without fetching every page. It runs as a Node.js stdio process configured with a Tavily API key, whose free tier includes 1,000 searches a month. Because it combines search with extraction and crawling, a single Tavily connection can power an end-to-end research loop: find sources, open them, and pull structured content back.

## Tools exposed

- tavily-search — real-time web search tuned for AI, with depth and domain filters
- tavily-extract — pull clean markdown content from one or more specific URLs
- tavily-crawl — crawl a site by following links to a configurable depth
- tavily-map — map a website's URL structure without fetching full page content

## Example queries you can run

- "Search for the three most-cited papers on MCP security and extract the abstract from each."
- "Crawl the docs at modelcontextprotocol.io two levels deep and list every page about transports."
- "Extract the full article at this URL as clean markdown so I can quote it."
- "Map the structure of example.com and tell me which sections have a pricing page."

## Details

- **Recommended model:** anthropic/claude-sonnet-4.5 — Claude Sonnet 4.5 orchestrates the search → extract → crawl loop well and knows when each tool applies. Use Haiku 4.5 for single search-and-extract calls.
- **Transport:** stdio
- **Authentication:** Required — A Tavily API key from app.tavily.com — the free tier gives 1,000 searches a month. Deploy a sandboxed hosted instance from the MCP Playground catalog and paste the key at deploy time.
- **Official source:** [tavily-ai/tavily-mcp on GitHub](https://github.com/tavily-ai/tavily-mcp)

## Frequently asked questions

### What is the Tavily MCP server?

It is the official MCP server from Tavily, a search engine designed for AI agents. It exposes search, extract, crawl and map tools so a model can find sources, read them and traverse sites through the Model Context Protocol.

### Which tools does the Tavily MCP server expose?

Four tools: tavily-search for real-time web search, tavily-extract to pull clean markdown from specific URLs, tavily-crawl to follow links across a site to a set depth, and tavily-map to map a site's URL structure.

### How is Tavily different from Brave Search or Perplexity?

Brave returns ranked links; Perplexity returns a finished cited answer. Tavily sits in between and adds extraction and crawling, so it is the best fit when an agent needs to open specific pages and pull structured content, not just get a list or a summary.

### Is there a free Tavily tier?

Yes. Tavily's free plan includes 1,000 searches per month, which is enough to evaluate the server and run light research workloads. Higher volumes need a paid plan, but the MCP tools are identical.

### How do I test a Tavily MCP server in the browser?

Open MCP Agent Studio, deploy the hosted Tavily server from the catalog, paste your Tavily API key, pick a model and ask it to research something. You can watch each tavily-search and tavily-extract call and its output live.

---

_Test this server across 40+ models on MCP Playground: https://mcpplaygroundonline.com/mcp-servers/tavily — free, no install._