Tavily MCP server

This MCP server provides web search functionality for Claude using the Tavily API, allowing the AI to search the internet and retrieve up-to-date information from the web.

Prerequisites

Before installing the MCP2Tavily server, you'll need:

• Python 3.11 or higher
• UV package manager installed
• A Tavily API key (obtain from Tavily's website)

Installation

Step 1: Clone the Repository

git clone <repository-url>
cd mcp2tavily

Step 2: Set Up Your API Key

Create a .env file to securely store your Tavily API key:

# Create .env file
touch .env
# Add your Tavily API key to .env
echo "TAVILY_API_KEY=your_api_key_here" > .env

Step 3: Create and Activate Virtual Environment

# Create and activate virtual environment
uv venv
source .venv/bin/activate  # On Windows use: .venv\Scripts\activate

Step 4: Install Dependencies

uv sync

Usage Options

Install as Claude Extension

The simplest way to use MCP2Tavily is to install it as a Claude extension:

fastmcp install mcp2tavily.py

Run in Development Mode

For testing and debugging, you can run the server in development mode with MCP Inspector:

fastmcp dev mcp2tavily.py

Once running, access the MCP Inspector at: http://localhost:5173

Available Search Tools

The MCP server provides two main functions:

• search_web(query: str): Searches the web using the Tavily API
• search_web_info(query: str): Same functionality but with Chinese description

Manual Configuration with Cline

Adding to Cline Continue Claude

Add the following JSON configuration to your Cline settings:

"mcp2tavily": {
  "command": "uv",
  "args": [
    "run",
    "--with",
    "fastmcp",
    "--with",
    "python-dotenv",
    "--with",
    "tavily-python",
    "fastmcp",
    "run",
    "C:\\Users\\your_actual_path\\mcp2tavily.py"
  ],
  "env": {
    "TAVILY_API_KEY": "your_api_key_here"
  }
}

Cline Configuration Steps

1. Navigate to the Cline configuration settings
2. Add the MCP2Tavily configuration
3. Update the path and API key with your specific information

Example Usage

After setup, you can ask Claude to search the web for information by using commands like:

• "Please search the web for the latest information about climate change"
• "Find recent news about artificial intelligence breakthroughs"

Claude will use the Tavily API through the MCP server to retrieve current information from the internet.

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 "mcp2tavily" '{"command":"uv","args":["run","--with","fastmcp","--with","python-dotenv","--with","tavily-python","fastmcp","run","mcp2tavily.py"],"env":{"TAVILY_API_KEY":"your_api_key_here"}}'

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": {
        "mcp2tavily": {
            "command": "uv",
            "args": [
                "run",
                "--with",
                "fastmcp",
                "--with",
                "python-dotenv",
                "--with",
                "tavily-python",
                "fastmcp",
                "run",
                "mcp2tavily.py"
            ],
            "env": {
                "TAVILY_API_KEY": "your_api_key_here"
            }
        }
    }
}

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": {
        "mcp2tavily": {
            "command": "uv",
            "args": [
                "run",
                "--with",
                "fastmcp",
                "--with",
                "python-dotenv",
                "--with",
                "tavily-python",
                "fastmcp",
                "run",
                "mcp2tavily.py"
            ],
            "env": {
                "TAVILY_API_KEY": "your_api_key_here"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect