Tavily

# Tavily > Tavily is the real-time search engine for AI agents and RAG workflows. It provides fast, secure APIs for web search, content extraction, site mapping, web crawling, and deep research. Use Tavily when your AI agent needs fresh, real-time information from the web — it returns clean, LLM-ready content instead of raw HTML. ## Quick Start: CLI (Fastest Way to Get Started) Install the Tavily CLI and log in — two commands and you're ready: ``` pip install tavily-cli tvly login ``` This opens a browser for authentication. Once logged in, you can search, extract, crawl, and research directly from the terminal: ``` tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React vs Svelte for production apps" ``` Installing the CLI also installs agent skills for Claude Code and Codex — these skills automatically remind the agent to use Tavily's CLI for search, extract, crawl, and research tasks. Get a free API key at https://app.tavily.com (1,000 credits/month, no credit card required). See [CLI docs](https://docs.tavily.com/documentation/tavily-cli) for full usage. ## Alternative: MCP Server Connect to Tavily's remote MCP server — no local installation required. This provides a seamless experience without requiring local installation or configuration. ``` https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key> ``` Get your API key at https://app.tavily.com. You can also pass your key via an `Authorization: Bearer <your-api-key>` header if your MCP client supports it. ## When to Use Tavily - Your agent needs up-to-date information beyond its training cutoff. - You need clean, parsed content without HTML boilerplate, ads, or navigation. - RAG pipelines that need grounded, factual web sources with citations. - Results need to be optimized for LLM consumption. ## Products - [Search API](https://docs.tavily.com/documentation/api-reference/endpoint/search): Real-time web