# tavily-mcp

> MCP Server

The Tavily MCP server enables AI systems to interact with data sources and tools using the Model Context Protocol, providing real-time web search and data extraction capabilities through Tavily's search

## Overview

- **Category:** AI
- **Language:** JavaScript
- **Stars:** 2327
- **Forks:** 21
- **Owner:** tavily-ai
- **GitHub:** https://github.com/tavily-ai/tavily-mcp
- **Created:** 2025-01-27T16:56:37+00:00
- **Updated:** 2025-03-28T20:38:42+00:00
- **Source:** https://model-context-protocol.com/servers/tavily-ai-model-context-protocol-server

## Setup

## Setup

Before you begin, ensure you have:

- [Tavily API key](https://app.tavily.com/home)
  - If you don't have a Tavily API key, you can sign up for a free account [here](https://app.tavily.com/home)
- [Claude Desktop](https://claude.ai/download) or [Cursor](https://cursor.sh)
- [Node.js](https://nodejs.org/) (v20 or higher)
  - You can verify your Node.js installation by running:
    - `node --version`
- [Git](https://git-scm.com/downloads) installed (only needed if using Git installation method)
  - On macOS: `brew install git`
  - On Linux: 
    - Debian/Ubuntu: `sudo apt install git`
    - RedHat/CentOS: `sudo yum install git`
  - On Windows: Download [Git for Windows](https://git-scm.com/download/win)

### Running with NPX 

```bash
npx -y tavily-mcp@0.1.4  
```

### Installing via Smithery

To install Tavily MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@tavily-ai/tavily-mcp):

```bash
npx -y @smithery/cli install @tavily-ai/tavily-mcp --client claude
```

Although you can launch a server on its own, it's not particularly helpful in isolation; instead, you should integrate it into an MCP client.

### Configuring Cline

1.  Open Cline in VS Code
2.  Click on the Cline icon in the sidebar
3.  Navigate to the "MCP Servers" tab ( 4 squares )
4.  Search "Tavily" and click "install"
5.  When prompted, enter your Tavily API key

Alternatively, you can manually set up the Tavily MCP server in Cline by modifying the `cline_mcp_settings.json` file and adding the Tavily server configuration with your API key.

### Configuring Cursor

1.  Open Cursor Settings
2.  Navigate to Features > MCP Servers
3.  Click on the "+ Add New MCP Server" button
4.  Fill out the information with the command `env TAVILY_API_KEY=your-api-key npx -y tavily-mcp@0.1.4` (replacing `your-api-key` with your actual API key).

### Configuring the Claude Desktop app

Modify the `claude_desktop_config.json` file by adding the Tavily server configuration with your API key.

### Git Installation

1.  Clone the repository: `git clone https://github.com/tavily-ai/tavily-mcp.git`
2.  Install dependencies: `npm install`
3.  Build the project: `npm run build`

Follow the configuration steps outlined in the [Configuring the Claude Desktop app](#configuring-the-claude-desktop-app-️) section above, using the below JSON configuration.


## Tools

## Available Tools

1.  Seamless interaction with the tavily-search and tavily-extract tools (allows interaction with Tavily's search and extraction capabilities).
2.  Real-time web search capabilities through the tavily-search tool (provides access to real-time web search).
3.  Intelligent data extraction from web pages via the tavily-extract tool (enables extraction of data from web pages).