# Tavily — MCP server on mcp.ai
> Connect your Tavily account and use 5 tools for web scraping straight from your AI agent. Connect with your own API key. Tavily offers search and data retrieval solutions, helping teams quickly locate and filter relevant information from documents, databases, or web sources.

By: mcp.ai · official
Page: https://mcp.ai/tavily

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_tavily?ms=1787293560000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/tavily/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/tavily/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/tavily/skill.md
Postman collection (v2.1): https://mcp.ai/tavily/postman.json

## Tools
- tavily_crawl(url: string, limit?: integer, format?: string, timeout?: integer, max_depth?: integer, max_breadth?: integer, instructions?: string, select_paths?: string[], exclude_paths?: string[], extract_depth?: string, include_usage?: boolean, allow_external?: boolean, include_images?: boolean, select_domains?: string[], exclude_domains?: string[], include_favicon?: boolean, chunks_per_source?: integer) — Tool to perform intelligent graph-based website crawling with parallel path exploration and content extraction. Use when you need to traverse and extract content from multiple pages of a website follo
- tavily_extract(urls: string|string[], query?: string, format?: string, timeout?: number, extract_depth?: string, include_usage?: boolean, include_images?: boolean, include_favicon?: boolean, chunks_per_source?: integer) — Tool to extract and parse web page content from specified URLs using Tavily's extract endpoint. Use when you need to retrieve clean, structured content from web pages with optional image extraction an
- tavily_get_usage() — Tool to retrieve API key and account usage statistics from Tavily. Use when you need to check credit consumption, limits, and per-endpoint usage for search, extract, crawl, map, and research operation
- tavily_map(url: string, limit?: integer, timeout?: integer, max_depth?: integer, max_breadth?: integer, instructions?: string, select_paths?: string[], exclude_paths?: string[], include_usage?: boolean, allow_external?: boolean, select_domains?: string[], exclude_domains?: string[]) — Tool to map a website and discover its pages. Use when you need to scan a website and get a structured list of URLs/pages it contains without extracting full content.
- tavily_search(query: string, max_results?: integer, search_depth?: string, include_answer?: boolean, include_images?: boolean, exclude_domains?: string[], include_domains?: string[], include_raw_content?: boolean) — Use this to perform a web search via the Tavily API; offers controls for search depth, content types, result count, and domain filtering. Requires an active Tavily connection (401 = auth failure). Rat

## Example prompts
- "What can I do in Tavily?"
- "Show me a summary of my Tavily account"

## Links
Docs: https://mcp.ai/docs/mcps/tavily
Website: https://mcp.ai/mcps/tavily