Tavily
About
Tavily MCP is a Model Context Protocol server that provides real-time web search, intelligent data extraction, web mapping, and web crawling tools. It integrates with MCP clients such as Claude Code and Cursor, and is designed for developers who need web-powered capabilities in their AI agent workflows.
Details
- Transport
- SSE
Explore
- Real-time web search via the tavily-search tool
- Intelligent data extraction from web pages via tavily-extract
- Web mapping tool that creates structured website maps
- Web crawler for systematic website exploration
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
TavilyCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
You can run Tavily MCP locally using npx -y tavily-mcp@latest, or connect to a remote MCP server at https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>. Set your Tavily API key via the TAVILY_API_KEY environment variable or pass it in the remote URL. Optionally configure default parameters for the tavily-search tool using the DEFAULT_PARAMETERS environment variable.
tavily_search
Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
tavily_extract
Extract content from URLs. Returns raw page content in markdown or text format.
tavily_crawl
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
tavily_map
Map a website's structure. Returns a list of URLs found starting from the base URL.
tavily_research
Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.
- tavily_search: Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
- tavily_extract: Extract content from URLs. Returns raw page content in markdown or text format.
- tavily_crawl: Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
- tavily_map: Map a website's structure. Returns a list of URLs found starting from the base URL.
- tavily_research: Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"tavily": {
"server": {
"command": "npx",
"args": [
"-y",
"tavily-mcp"
],
"env": {
"TAVILY_API_KEY": "",
"DEFAULT_PARAMETERS": ""
}
}
}
}
}McpServers
{
"server": {
"command": "npx",
"args": [
"-y",
"tavily-mcp"
],
"env": {
"TAVILY_API_KEY": "",
"DEFAULT_PARAMETERS": ""
}
}
}Transport
"stdio"Package
"tavily-mcp"Registry
"npm"Tavily gives AI agents real-time web access through search, extraction, and research APIs. Its connector helps assistants ground answers in live data, extract relevant content, and support production-agent workflows with security controls.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
