📌Overview

Purpose: To provide an efficient MCP server that leverages the Tavily API for performing accurate and user-friendly search queries.

Overview: The Tavily Search MCP server enables users to execute searches based on custom queries, returning results in a user-friendly text format that includes AI-generated responses, URIs, and titles. It is compatible with various operating systems and provides installation options through different methods such as Smithery and Docker Compose.

Key Features:

• Search Functionality: Performs tailored searches using the Tavily API with required and optional parameters for enhanced user experience.

• User-Friendly Output: Returns search results in a clear, accessible text format, including relevant details like event descriptions and links for further information.

---

Tavily-Search MCP Server

Overview

The Tavily-Search MCP server utilizes the Tavily API to perform searches based on specified queries, returning results in text format including AI responses, URIs, and titles.

Components

• Search Tool:
  • Command: search
  • Required Argument: query
  • Optional Argument: search_depth (basic or advanced)

Installation

Via Smithery

To install Tavily Search for Claude Desktop automatically:

npx -y @smithery/cli install tavily-search --client claude

Manual Installation

1. Clone the repository:

   git clone https://github.com/Tomatio13/mcp-server-tavily.git
   

2. Open the Claude Desktop configuration file:
   • MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
   • Windows: C:\Users\[username]\AppData\Roaming\Claude\claude_desktop_config.json
3. Modify the configuration:

   "mcpServers": {
     "tavily-search": {
       "command": "uv",
       "args": [
         "--directory",
         "C:\\your_path\\mcp-server-tavily",
         "run",
         "tavily-search"
       ],
       "env": {
         "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
         "PYTHONIOENCODING": "utf-8"
       }
     }
   }
   

4. Restart Claude Desktop.

Usage

In Claude Desktop, to initiate a search, simply input a query:

Please search in detail for today's events in Kamakura

Sample Response:

According to the search results, the following events start today, December 1st:
"Kamakura Promotion Photo Contest 2025"
Period: December 1, 2024 - January 31, 2025
A photo contest for those who love Kamakura
Applications start accepting from today

Log Storage

Logs are stored in:

• Windows: C:\Users\[username]\AppData\Roaming\Claude\logs\mcp-server-tavily-search

Running with Cursor

1. Create a shell script (e.g., script.sh):

   #!/bin/bash
   TARGET_DIR=/path/to/mcp-server-tavily
   cd "${TARGET_DIR}"
   export TAVILY_API_KEY="your-api-key"
   export PYTHONIOENCODING=utf-8
   uv --directory $PWD run tavily-search
   

2. Configure Cursor's MCP Server settings:
   • Name: tavily-search
   • Type: command
   • Command: /path/to/your/script.sh
3. Save the settings and use Cursor's Composer-Agent to search.

Running in Local Environment Using Docker Compose

Purpose

This section describes how to set up and run an MCP server and client in a local environment using Docker Compose.

Steps

1. Install Docker.
2. Clone the repository:

   git clone https://github.com/Tomatio13/mcp-server-tavily.git
   

3. Run Docker Compose:

   docker compose up -d
   

4. Execute the client:

   docker exec mcp_server uv --directory /usr/src/app/mcp-server-tavily/src run client.py