Tavily MCP Server

What does “Tavily” MCP Server do?

The Tavily MCP Server is a Model Context Protocol (MCP) server that empowers AI assistants with advanced web search capabilities using Tavily’s search API. By integrating with this server, AI models can perform robust web searches, retrieve direct answers to complex questions, and gather recent news articles with AI-extracted relevant content. This enhances development workflows by allowing tasks such as comprehensive information retrieval, evidence-backed question answering, and up-to-date news aggregation—all accessible as tools or resources within LLM-powered environments. The Tavily MCP Server thus bridges the gap between AI assistants and real-time, high-quality web data, streamlining research, automation, and context-aware AI solutions.

List of Prompts

• tavily_web_search – Search the web using Tavily’s AI-powered search engine.
• tavily_answer_search – Search the web and get an AI-generated answer with supporting evidence.
• tavily_news_search – Search recent news articles with Tavily’s news search.

List of Resources

• No explicit resources section found in the repository documentation.

List of Tools

• tavily_web_search
  Performs comprehensive web searches with AI-powered content extraction.
  • Parameters: query, max_results, search_depth, include_domains, exclude_domains
• tavily_answer_search
  Web search and generates direct answers with supporting evidence.
  • Parameters: query, max_results, search_depth, include_domains, exclude_domains
• tavily_news_search
  Searches recent news articles with publication dates.
  • Parameters: query, max_results, days, include_domains, exclude_domains

Use Cases of this MCP Server

• Comprehensive Web Search
  Developers can perform wide-ranging searches for any topic, with results extracted and summarized by AI for easy consumption in their workflows.
• Direct Question Answering
  Enables AI assistants to return direct, evidence-backed answers to user queries, improving accuracy and reducing research time.
• News Aggregation
  Retrieve and summarize the latest news articles related to a query, keeping users up-to-date on current events or trends.
• Domain-Specific Search
  Restrict searches to or exclude specific domains, allowing for focused research (e.g., academic, corporate, or industry-specific information).
• Evidence Collection
  Gather supporting links and references for answers and reports, enabling transparent and verifiable outputs for decision-making or documentation.

How to set it up

Windsurf

1. Ensure Python 3.11+ and a Tavily API key are available.
2. Install the package:

   pip install mcp-tavily
   

3. Locate your Windsurf configuration file.
4. Add the Tavily MCP Server to your mcpServers:

   {
     "mcpServers": {
       "tavily": {
         "command": "mcp-tavily",
         "args": []
       }
     }
   }
   

5. Save the file and restart Windsurf.
6. Verify the server is running and accessible.

Securing API Keys:
Use environment variables for your Tavily API key:

{
  "mcpServers": {
    "tavily": {
      "command": "mcp-tavily",
      "env": {
        "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY"
      },
      "inputs": {}
    }
  }
}

Claude

1. Install mcp-tavily in your environment.
2. Edit Claude’s configuration file to include:

   {
     "mcpServers": {
       "tavily": {
         "command": "mcp-tavily"
       }
     }
   }
   

3. Add your Tavily API key in the env section as above.
4. Restart Claude and confirm connection.

Cursor

1. Ensure mcp-tavily is installed.
2. Open Cursor’s configuration.
3. Insert:

   {
     "mcpServers": {
       "tavily": {
         "command": "mcp-tavily"
       }
     }
   }
   

4. Place your Tavily API key in the env field if supported.
5. Save and restart Cursor.

Cline

1. Install mcp-tavily via pip or uv.
2. Edit the Cline config file:

   {
     "mcpServers": {
       "tavily": {
         "command": "mcp-tavily"
       }
     }
   }
   

3. Add your API key to the env section.
4. Save and restart Cline.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "tavily": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “tavily” to whatever the actual name of your MCP server is (e.g., “github-mcp”, “weather-api”, etc.) and replace the URL with your own MCP server URL.

Overview

Our opinion

The Tavily MCP Server provides a well-defined set of search tools, clear prompt templates, and straightforward installation and configuration steps. However, it lacks explicit resource definitions and does not mention advanced MCP features like roots or sampling. Given its focused functionality and good documentation, but missing some MCP primitives, we rate it a 7/10 for practical use.

MCP Score