Tavily

by Tavily
Repository Docs npm
Web & Search
searchwebresearchextractionagents

Summary

Web search and content extraction optimized for AI agents — fast, relevance-ranked results with source content.

Features

  • AI-optimized web search
  • Relevance-ranked results
  • Built-in content extraction
  • Source-grounded answers
  • Fast responses

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it, filling in the environment variables with your own values.
  3. Restart the agent — the "Tavily" tools will be available.
{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp"
      ],
      "env": {
        "TAVILY_API_KEY": "tvly-YOUR_API_KEY"
      }
    }
  }
}

Description

The Tavily MCP server provides advanced web search and content extraction tuned for AI agents. It returns relevance-ranked results with extracted page content, so assistants can research topics and cite sources without a separate scraping step.

Related MCP Servers

Perplexity Ask

by Perplexity

Ask Perplexity's Sonar API real-time, web-grounded questions and get cited answers inside your agent.

Web & Search
searchresearchcitations

Brave Search

by Brave

Search the web with the Brave Search API — web, image, video, and news results plus rich results and AI summaries.

Web & Search
searchwebprivacy

Exa Search

by Exa

Real-time web search and crawling built for AI — neural search with configurable tools and live content retrieval.

Web & Search
searchwebneural-search

Firecrawl

by Firecrawl

Search, scrape, crawl, and extract structured data from the web — with JS rendering, batch scraping, and LLM-powered extraction.

Web & Search
scrapingcrawlingweb
Browse all MCP servers →