MCPdir β€” MCP Server Directory
πŸ‡¬πŸ‡§ πŸ‡ͺπŸ‡Έ

Tavily MCP

by Tavily

Real-time web search, extraction, mapping, and crawling for AI agents

search Node.js Beginner Self-hostable Verified
⭐ 1.3k stars πŸ“… Updated: 1mo ago

Description

Production-ready MCP server providing real-time web search, intelligent data extraction, website mapping, and systematic web crawling. Optimized for AI agent research workflows with structured results and context-aware ranking. The search tool delivers fresh, relevant results from across the web, while extract pulls structured data from specific URLs. Web map discovers site structure for comprehensive coverage, and web crawl systematically processes multiple pages. Supports both local STDIO transport via npx and a hosted remote endpoint for zero-install access. Free tier available for getting started.

βœ… Best for

AI agents that need real-time web information, structured extraction, and research capabilities

⏭️ Skip if

You need unlimited free search or already have a web search MCP that meets your needs

πŸ’‘ Use cases

  • Real-time web research and fact-checking within AI assistant conversations
  • Extracting structured data from specific web pages for analysis
  • Mapping website structures to discover available content and endpoints
  • Systematic web crawling for comprehensive data gathering

πŸ‘ Pros

  • βœ“ Purpose-built for AI agent workflows with optimized result formatting
  • βœ“ Free tier available β€” easy to get started without payment
  • βœ“ Dual access via local npx or hosted remote MCP endpoint
  • βœ“ Four complementary tools covering search, extract, map, and crawl

πŸ‘Ž Cons

  • βœ— Free tier has limited daily queries β€” paid plan needed for production use
  • βœ— Search results may vary in depth compared to traditional search engines
  • βœ— Crawling large sites can be slow and consume significant API quota

πŸ”§ Exposed tools (4 tools)

ToolCategoryDescription
web_crawlcrawlingSystematically crawl multiple pages of a website
tavily_extractextractionExtract structured data from a specific web page URL
web_mapmappingMap the structure of a website to discover available pages
tavily_searchsearchSearch the web in real-time with AI-optimized results

⚑ Installation

Prerequisites:

  • β€’ Node.js v18+
  • β€’ Tavily API key (free tier available)
  • β€’ API key required

Check Claude Code documentation to configure this MCP server.

πŸ’‘ Tips & tricks

Start with the free tier to evaluate. Use tavily_search for broad queries and tavily_extract when you need structured data from a known URL. The web_map tool is great for discovering all pages on a site before targeted extraction.

πŸ”„ Alternatives

Quick info

Author
Tavily
License
MIT
Runtime
Node.js 18+
Transport
stdio
Category
search
Difficulty
Beginner
Self-hostable
βœ…
Auth
β€”
Docker
β€”
Version
latest
Updated
Feb 28, 2026

Client compatibility

  • βœ… Claude Code
  • βœ… Cursor
  • ❓ VS Code Copilot
  • ❓ Gemini CLI
  • ❓ Windsurf
  • ❓ Cline
  • ❓ JetBrains AI
  • ❓ Warp

Platforms

🍎 macOS 🐧 Linux πŸͺŸ Windows