Tavily MCP
Real-time web search optimized for AI agents
BestMCPTools
Tavily MCP
bestmcptools.org
Maintenance status
ActiveHow to Install Tavily MCP
$npx tavily-mcp@latestRequires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.
Setup by client
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"tavily-mcp": {
"command": "npx",
"args": [
"tavily-mcp@latest"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"tavily-mcp": {
"command": "npx",
"args": [
"tavily-mcp@latest"
]
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"tavily-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"tavily-mcp@latest"
]
}
}
}Claude Code (terminal)
claude mcp add tavily-mcp -- npx tavily-mcp@latestAdd any API keys or environment variables the server's README lists.
About Tavily MCP
Tavily is a web search API built specifically for AI agents; it returns structured, LLM-friendly results with relevant snippets and source URLs. The MCP server lets any MCP-compatible agent search the web in real-time. When you need whole pages rather than snippets, connect Exa to Claude for semantic search or use the Firecrawl MCP setup to scrape and crawl sites.
Tavily MCP is a Search MCP server designed for researchers, analysts, and engineers building grounded agents. It enables giving AI assistants live, source-grounded web access by wrapping a search provider and page-fetch step as MCP tools. Key capabilities include live web search with snippets and urls, optional full-page fetch for cited sources, configurable result counts and freshness windows, and structured tool calls that work cleanly inside an LLM context. It integrates with Google, Bing, Brave, Tavily, Exa, Perplexity, and SerpAPI, and is best suited for researchers, analysts, and engineers building grounded agents who need research and competitive analysis.
Key Features
- search
- web-search
- real-time
- research
- Live web search with snippets and URLs
- Optional full-page fetch for cited sources
Pricing
Freemium: from Free (1000 searches/month free)
Pros & Cons
Pros
- Lets the assistant answer about events past its training cutoff
- Cites sources you can actually click
- Replaces most simple RAG pipelines
Cons
- Quality depends on the underlying search provider
- Token costs scale with how much page content you pull
- Rate limits can bite on bursty agent runs
Best For
- Research and competitive analysis
- Source-grounded answers in chat UIs
- Fact-checking long-form drafts
- Replacing manual Googling in agent loops
Our Take on Tavily MCP
The most popular AI-native web search MCP: fast, reliable, and well-documented.