Tavily MCP Server

Researchstdiov0.3.1
Repository

MCP server for Tavily's AI-optimized search engine. Designed specifically for LLM agents and RAG applications, providing concise, factual search results with source attribution. Supports general web search, news search, and direct Q&A extraction. Returns pre-processed content optimized for AI consumption with relevance scoring and content deduplication.

Connect

Add this configuration to .claude/mcp.json

{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp"
      ],
      "env": {
        "TAVILY_API_KEY": "<YOUR_TAVILY_API_KEY>"
      }
    }
  }
}

Tools (2)

tavily_search

Perform an AI-optimized web search and return relevant results with content.

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query"
    },
    "topic": {
      "enum": [
        "general",
        "news"
      ],
      "type": "string",
      "description": "Search topic category"
    },
    "max_results": {
      "type": "integer",
      "description": "Maximum number of results to return (default 5)"
    },
    "search_depth": {
      "enum": [
        "basic",
        "advanced"
      ],
      "type": "string",
      "description": "Search depth (basic is faster, advanced is more thorough)"
    },
    "exclude_domains": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Exclude results from these domains"
    },
    "include_domains": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Only include results from these domains"
    }
  }
}

tavily_extract

Extract and parse content from one or more URLs into clean text.

{
  "type": "object",
  "required": [
    "urls"
  ],
  "properties": {
    "urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "URLs to extract content from"
    }
  }
}

Resources

This server does not expose any resources.

Prompts

This server does not expose any prompts.

Server Information

Author
Tavily (@tavily-ai)
Repository
https://github.com/tavily-ai/tavily-mcp
License
MIT
Version
0.3.1
Stars
1,820
Last Updated
May 26, 2026
Tavily MCP Server - MCP Server | OpenModels