by tavily-ai
Provides real-time web search, intelligent data extraction, site mapping, and crawling capabilities via MCP tools.
Tavily MCP delivers a suite of tools that enable real‑time web searching, precise content extraction, automatic site mapping, and systematic crawling. These capabilities are exposed through the Model Context Protocol, allowing LLM‑based agents to retrieve and process live web information.
npx -y tavily-mcp@latest
TAVILY_API_KEY
environment variable (or configure it in your MCP client settings).https://mcp.tavily.com/mcp/?tavilyApiKey=<YOUR_API_KEY>
.tavily-search
, tavily-extract
, tavily-map
, and tavily-crawl
from within your LLM prompts or API calls.Q: Do I need to run the server locally?
A: No. You can either run the server locally with npx
or use the hosted remote endpoint by providing your API key.
Q: Which environment variable holds the API key?
A: TAVILY_API_KEY
.
Q: Can I use Tavily MCP with OpenAI models?
A: Yes. Include a tool definition of type mcp
in the OpenAI request and point server_url
to the remote endpoint.
Q: What clients are supported out of the box? A: Claude Desktop, Cursor, VS Code, Cline, and any MCP‑compatible client.
Q: Is there a rate limit? A: Rate limits are governed by your Tavily account tier; refer to the Tavily dashboard for details.
The Tavily MCP server provides:
Connect directly to Tavily's remote MCP server instead of running it locally. 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.
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 ...
Click the install button
You should see the MCP is now installed, if the blue slide is not already turned on, manually turn it on. You also need to edit the configuration to include your own Tavily API key.
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": {}
}
}
}
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.
click 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.
Retrun to the chat screen and you will see the Tavily Remote MCP is now connected to Claude desktop.
Allow models to use remote MCP servers to perform tasks.
<your-api-key>
, you can get a Tavily API key herefrom 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)
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>"
]
}
}
Before you begin, ensure you have:
node --version
brew install git
sudo apt install git
sudo yum install git
npx -y tavily-mcp@latest
To install Tavily MCP Server for Claude Desktop automatically via Smithery:
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. Below is an example of how to configure the Claude Desktop app to work with the tavily-mcp server.
This repository will explain how to configure VS Code, Cursor and Claude Desktop to work with the tavily-mcp server.
For one-click installation, click one of the install buttons below:
First check if there are install buttons at the top of this section that match your needs. If you prefer manual installation, follow these steps:
Add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P
(or Cmd + Shift + P
on macOS) and typing Preferences: Open User Settings (JSON)
.
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "tavily_api_key",
"description": "Tavily API Key",
"password": true
}
],
"servers": {
"tavily": {
"command": "npx",
"args": ["-y", "tavily-mcp@latest"],
"env": {
"TAVILY_API_KEY": "${input:tavily_api_key}"
}
}
}
}
}
Optionally, you can add it to a file called .vscode/mcp.json
in your workspace:
{
"inputs": [
{
"type": "promptString",
"id": "tavily_api_key",
"description": "Tavily API Key",
"password": true
}
],
"servers": {
"tavily": {
"command": "npx",
"args": ["-y", "tavily-mcp@latest"],
"env": {
"TAVILY_API_KEY": "${input:tavily_api_key}"
}
}
}
}
The easiest way to set up the Tavily MCP server in Cline is through the marketplace with a single click:
Alternatively, you can manually set up the Tavily MCP server in Cline:
Open the Cline MCP settings file:
# Using Visual Studio Code
code ~/Library/Application\ Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
# Or using TextEdit
open -e ~/Library/Application\ Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
code %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
Add the Tavily server configuration to the file:
Replace your-api-key-here
with your actual Tavily API key.
{
"mcpServers": {
"tavily-mcp": {
"command": "npx",
"args": ["-y", "tavily-mcp@latest"],
"env": {
"TAVILY_API_KEY": "your-api-key-here"
},
"disabled": false,
"autoApprove": []
}
}
}
Save the file and restart Cline if it's already running.
When using Cline, you'll now have access to the Tavily MCP tools. You can ask Cline to use the tavily-search and tavily-extract tools directly in your conversations.
# Create the config file if it doesn't exist
touch "$HOME/Library/Application Support/Claude/claude_desktop_config.json"
# Opens the config file in TextEdit
open -e "$HOME/Library/Application Support/Claude/claude_desktop_config.json"
# Alternative method using Visual Studio Code (requires VS Code to be installed)
code "$HOME/Library/Application Support/Claude/claude_desktop_config.json"
code %APPDATA%\Claude\claude_desktop_config.json
Replace your-api-key-here
with your actual Tavily API key.
{
"mcpServers": {
"tavily-mcp": {
"command": "npx",
"args": ["-y", "tavily-mcp@latest"],
"env": {
"TAVILY_API_KEY": "your-api-key-here"
}
}
}
}
git clone https://github.com/tavily-ai/tavily-mcp.git
cd tavily-mcp
npm install
npm run build
Follow the configuration steps outlined in the Configuring the Claude Desktop app section above, using the below JSON configuration.
Replace your-api-key-here
with your actual Tavily API key and /path/to/tavily-mcp
with the actual path where you cloned the repository on your system.
{
"mcpServers": {
"tavily": {
"command": "npx",
"args": ["/path/to/tavily-mcp/build/index.js"],
"env": {
"TAVILY_API_KEY": "your-api-key-here"
}
}
}
}
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "tavily": { "command": "npx", "args": [ "-y", "tavily-mcp@latest" ], "env": { "TAVILY_API_KEY": "<YOUR_API_KEY>" } } } }
Discover more MCP servers with similar functionality and use cases
by firecrawl
Adds powerful web scraping, crawling, and search capabilities to LLM clients through a Model Context Protocol (MCP) server.
by mendableai
Firecrawl MCP Server is an official Model Context Protocol (MCP) server implementation that integrates with Firecrawl to provide powerful web scraping capabilities to Large Language Models (LLMs). It acts as a bridge between LLMs and the web, allowing them to access and process web content for various tasks.
by iFurySt
RedNote-MCP is an MCP server designed to access content from RedNote (XiaoHongShu, xhs), a popular Chinese social media and e-commerce platform. It enables programmatic interaction with RedNote for data retrieval and automation.
by zcaceres
fetch-mcp is a flexible HTTP fetching server designed to retrieve web content in various formats. It acts as a server that can fetch HTML, JSON, Markdown, or plaintext from specified URLs, enabling on-demand fetching and transformation of web content.
by apify
An MCP server for Apify Actors, allowing AI assistants to use any of the 3,000+ pre-built cloud tools for web scraping and automation.
by openbnb-org
The mcp-server-airbnb is an MCP (Multi-Cloud Platform) server designed to interact with Airbnb. It provides tools for searching Airbnb listings and retrieving detailed information about specific listings.
by cnych
A free SEO tool MCP (Model Control Protocol) service based on Ahrefs data, offering features like backlink analysis, keyword research, and traffic estimation.
by tinyfish-io
AgentQL MCP Server is a Model Context Protocol (MCP) server that integrates AgentQL's data extraction capabilities, enabling AI agents to get structured data from the unstructured web.
by oxylabs
Bridge AI models and the internet, delivering clean, structured data from any website through a single API.