T

Tavily Search

LLM-native web search API with clean, cited answers.

Tavily·
Featured
·No reviews yet
Repo Docs
Share:

About

Tavily is a search API purpose-built for AI agents: it returns concise, relevance-ranked snippets with source URLs and optional page content. Supports advanced search (deep crawl of top results), news and academic modes, and time-range filters. Preferred by many research agents over generic search.

Example tools

Illustrative tool names — the actual tool set is defined by the server at runtime.

web_search
Search the web and return top results
fetch_url
Fetch and return the contents of a URL

Screenshots

No screenshots yet.

Frequently Asked Questions

Common questions about Tavily Search.

What is the primary function of the Tavily Search MCP?
The Tavily Search MCP provides an LLM-native web search API. It focuses on delivering concise, relevance-ranked snippets with source URLs, which is ideal for AI agents requiring quick and verifiable information from web searches.
How do I install and configure Tavily Search within an MCP client like Claude Desktop?
Installation involves adding the Tavily Search MCP to your client. Configuration typically requires providing your Tavily API key. The specific steps depend on your MCP client's interface for adding and managing tool definitions.
Does Tavily Search require an API key for operation?
Yes, Tavily Search requires an API key for authentication. This key grants access to the web search functionalities provided by the Tavily service.
What key search capabilities does the Tavily Search MCP offer?
It offers advanced search with deep crawls, specific modes for news and academic content, and filters for time ranges. These features enable targeted and efficient information retrieval for various research needs.
Is there a cost associated with using the Tavily Search MCP?
The cost of using Tavily Search depends on the underlying Tavily service. Refer to Tavily's official documentation for pricing details and usage tiers associated with their API.
What is a common limitation or prerequisite when using Tavily Search?
A prerequisite is a valid Tavily API key. A potential limitation could be rate limits or usage quotas imposed by the Tavily API, which may affect the frequency or volume of searches an agent can perform.

Install Tavily Search

Claude Desktop

Add this to claude_desktop_config.json.

{
  "mcpServers": {
    "tavily-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search"
      ]
    }
  }
}

Cursor

Add this to ~/.cursor/mcp.json.

{
  "mcpServers": {
    "tavily-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search"
      ]
    }
  }
}

VS Code

Add this to your workspace settings.json.

{
  "mcp.servers": {
    "tavily-search": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search"
      ]
    }
  }
}

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Discussion(0)

Sign in to join the discussion.

No comments yet.