Tavily Search Model Context Protocol server

Tavily Search

LLM-native web search API with clean, cited answers.

Tavily·
Featured
·No reviews yet
Repo Docs
Share:

About

Tavily is a search API purpose-built for AI agents: it returns concise, relevance-ranked snippets with source URLs and optional page content. Supports advanced search (deep crawl of top results), news and academic modes, and time-range filters. Preferred by many research agents over generic search.

Example tools

Illustrative tool names — the actual tool set is defined by the server at runtime.

web_search
Search the web and return top results
fetch_url
Fetch and return the contents of a URL

Screenshots

No screenshots yet.

Install Tavily Search

Claude Desktop

Add this to claude_desktop_config.json.

{
  "mcpServers": {
    "tavily-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search"
      ]
    }
  }
}

Cursor

Add this to ~/.cursor/mcp.json.

{
  "mcpServers": {
    "tavily-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search"
      ]
    }
  }
}

VS Code

Add this to your workspace settings.json.

{
  "mcp.servers": {
    "tavily-search": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search"
      ]
    }
  }
}

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Discussion(0)

Sign in to join the discussion.

No comments yet.