Tavily Search MCP server for AI agents

This server provides internet search capabilities to MCP clients using the Tavily API. With this implementation, your MCP-enabled applications can perform web searches to retrieve current information from across the internet.

Installation

Prerequisites

Before setting up the Tavily search MCP server, you need:

A Tavily API key (obtain this from Tavily's website)
Python installed on your system

Setup Steps

Clone the repository or download the source code to your local machine
Create a .env file in the root directory of the project and add your Tavily API key:
```
TAVILY_API_KEY=your_api_key_here
```
Install the required dependencies (if not already mentioned in the README, you may need to run a command such as):
```
pip install -r requirements.txt
```

Configuration

To enable the Tavily search MCP server in your MCP configuration, add the following to your MCP config file:

{
  "mcpServers": {
    "tavily_search": {
      "command": "uv",
      "args": [
        "--directory",
        "%USERPROFILE%/Documents/GitHub/mcp-tavily-search",
        "run",
        "python",
        "main.py"
      ]
    }
  }
}

Note: You may need to adjust the directory path to match where you've actually stored the mcp-tavily-search code on your system.

Using the Search Functionality

Once configured, your MCP client applications can make search requests through this server. The server will process these requests, call the Tavily API with your credentials, and return the search results.

The specific API format for making requests will depend on your client application, but generally you'll be able to:

Perform web searches with various query parameters
Receive structured search results that can be used in your application logic

Refer to your MCP client documentation for specific details on how to interface with this search functionality in your application.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "tavily_search" '{"command":"uv","args":["--directory","%USERPROFILE%/Documents/GitHub/mcp-tavily-search","run","python","main.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "tavily_search": {
            "command": "uv",
            "args": [
                "--directory",
                "%USERPROFILE%/Documents/GitHub/mcp-tavily-search",
                "run",
                "python",
                "main.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "tavily_search": {
            "command": "uv",
            "args": [
                "--directory",
                "%USERPROFILE%/Documents/GitHub/mcp-tavily-search",
                "run",
                "python",
                "main.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect