Tavily Mcp Server Ai Web Search Extraction

---
name: "Tavily MCP Server for AI-Powered Web Search and Extraction"
slug: "tavily-mcp-server-ai-web-search-extraction"
description: "An official MCP server from Tavily that provides AI agents with real-time web search, page extraction, site mapping, and web crawling capabilities. Connects to Tavily's search API to deliver structured, relevant results optimized for LLM consumption."
github_stars: 1615
verification: "security_reviewed"
source: "https://github.com/tavily-ai/tavily-mcp"
category: "Research & Scraping"
framework: "MCP"
tool_ecosystem:
  github_repo: "tavily-ai/tavily-mcp"
  github_stars: 1615
  npm_package: "tavily-mcp"
  npm_weekly_downloads: 47930
---

# Tavily MCP Server for AI-Powered Web Search and Extraction

An official MCP server from Tavily that provides AI agents with real-time web search, page extraction, site mapping, and web crawling capabilities. Connects to Tavily's search API to deliver structured, relevant results optimized for LLM consumption.

## Installation

Use the upstream install or setup path that matches your environment:
- npx -y tavily-mcp@latest

Requirements and caveats from upstream:
- [Node.js](https://nodejs.org/) (v20 or higher)
- You can verify your Node.js installation by running:
- node --version

Basic usage or getting-started notes:
- **Note:** When using the remote MCP, you can specify default parameters for all requests by including a DEFAULT_PARAMETERS header containing a JSON object with your desired defaults. Example:
- Run claude to start Claude Code
- **B. Using other MCP Clients (Example: Cursor):**

- Source: https://github.com/tavily-ai/tavily-mcp
- Extracted from upstream docs: https://raw.githubusercontent.com/tavily-ai/tavily-mcp/HEAD/README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/tavily-mcp-server-ai-web-search-extraction/)