GitHub

/tavily-ai/tavily-mcpGitHub Repo stars

NPM

@tavily/mcpnpm
Compatible with both Cursor and Claude Desktop!Tavily MCP is also compatible with any MCP client.
Check out our tutorial on combining Tavily MCP with Neo4j MCP server!
Tavily MCP Demo
The Model Context Protocol (MCP) is an open standard that enables AI systems to interact seamlessly with various data sources and tools, facilitating secure, two-way connections.Developed by Anthropic, the Model Context Protocol (MCP) enables AI assistants like Claude to seamlessly integrate with Tavily’s advanced search and data extraction capabilities. This integration provides AI models with real-time access to web information, complete with sophisticated filtering options and domain-specific search features.

​
Remote MCP Server

The easiest way to take advantage of Tavily MCP is by using the remote URL. This provides a seamless experience without requiring local installation or configuration. Simply use the remote MCP server URL with your Tavily API key: 
https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>
Get your Tavily API key from tavily.com.

​
Connect to Cursor

Install MCP Server Click the ⬆️ Add to Cursor ⬆️ button, this will do most of the work for you but you will still need to edit the configuration to add your API-KEY. You can get a Tavily API key here. once you click the button you should be redirect to Cursor … You will then be redirected to your mcp.json file where you have to add your-api-key. 
{
  "mcpServers": {
    "tavily-remote-mcp": {
      "command": "npx -y mcp-remote https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>",
      "env": {}
    }
  }
}

​
Connect to Claude Desktop

Claude desktop now supports adding integrations which is currently in beta. An integration in this case is the Tavily Remote MCP, below I will explain how to add the MCP as an integration in Claude desktop. Open claude desktop, click the button with the two sliders and then navigate to add integrations. Name the integration and insert the Tavily remote MCP url with your API key. You can get a Tavily API key here. Click Add to confirm.

​
OpenAI

Allow models to use remote MCP servers to perform tasks.
  • You first need to export your OPENAI_API_KEY
  • You must also add your Tavily API-key to <your-api-key>, you can get a Tavily API key here
from openai import OpenAI

client = OpenAI()

resp = client.responses.create(
    model="gpt-4.1",
    tools=[
        {
            "type": "mcp",
            "server_label": "tavily",
            "server_url": "https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>",
            "require_approval": "never",
        },
    ],
    input="Do you have access to the tavily mcp server?",
)

print(resp.output_text)

​
Clients that don’t support remote MCPs

mcp-remote is a lightweight bridge that lets MCP clients that can only talk to local (stdio) servers securely connect to remote MCP servers over HTTP + SSE with OAuth-based auth, so you can host and update your server in the cloud while existing clients keep working. It serves as an experimental stop-gap until popular MCP clients natively support remote, authorized servers. 
{
    "tavily-remote": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>"
      ]
    }
}
Alternatively, you can also run the MCP server locally.

​
Local Installation

​
Prerequisites

npx -y tavily-mcp@0.1.3
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 MCP Clients

Note: Requires Cursor version 0.45.6 or higher
To set up the Tavily MCP server in Cursor:
  1. Open Cursor Settings
  2. Navigate to Features > MCP Servers
  3. Click on the ”+ Add New MCP Server” button
  4. Fill out the following information:
    • Name: Enter a nickname for the server (e.g., “tavily-mcp”)
    • Type: Select “command” as the type
    • Command: Enter the command to run the server: 
      env TAVILY_API_KEY=tvly-YOUR_API_KEY npx -y tavily-mcp@0.1.3
      Replace tvly-YOUR_API_KEY with your Tavily API key from app.tavily.com/home
Cursor Interface Example

​
Usage Examples

​
Troubleshooting

​
Acknowledgments

Model Context Protocol

For the MCP specification

Anthropic

For Claude Desktop