Search

Tavily MCP

RAG-focused search with native LangChain/LlamaIndex integration. Specializes in deep research with extract and crawl capabilities.

50% Pass ⚠️Key Required 🔑Tested 📅
50% (1/2 tasks)
View on GitHubby Tavily (Nebius)
README badge
MCP Select Tavily MCP benchmark badge
[![MCP Select](https://mcpselect.com/badges/tavily-mcp.svg)](https://mcpselect.com/servers/tavily-mcp/)

Benchmark results

Pass Rate
50%(5 tasks)
50% (1/2 tasks)
Speed675ms p50675ms p50
Tested OnJun 8, 20265 tools found
MetricValue
Tools discovered5 tools found
ScopeCloud / Remote
PricingFreemium
Auth requirementRequires TAVILY_API_KEY
Verdict50% pass rate on 2 tasks

Install config

Claude Desktop (macOS)
{"mcpServers": {"tavily": {"command": "npx", "args": ["-y", "tavily-mcp@latest"], "env": {"TAVILY_API_KEY": "your-key"}}}}
Cursor
{"mcpServers": {"tavily": {"command": "npx", "args": ["-y", "tavily-mcp@latest"], "env": {"TAVILY_API_KEY": "your-key"}}}}
VS Code
// .vscode/mcp.json
{
  "servers": {
    "tavily": {
      "command": "npx",
      "args": ["-y", "tavily-mcp@latest"],
      "env": {"TAVILY_API_KEY": "your-key"}
    }
  }
}

Pros

  • +Server starts successfully
  • +Tools are discoverable

Cons

  • Some tasks failed testing
  • May require API key

Best for

Web search, content extraction, research

Related servers in Search

Frequently asked questions

How do I install Tavily MCP?

Copy the config above into your AI assistant's MCP settings file:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Cursor: Settings → MCP → Add Server
  • VS Code: .vscode/mcp.json
Does it require an API key?

Yes. You need to set the TAVILY_API_KEY environment variable. We could not test this server without credentials, so our evaluation is based on documentation and community reports.

How were these results measured?

We run each server through a standardized test harness that:

  1. Installs the server via npx in a fresh environment
  2. Discovers available tools using the MCP SDK
  3. Executes real tasks (navigate, click, screenshot, etc.)
  4. Validates outputs with semantic assertions (not string matching)
  5. Measures latency percentiles and pass rate

All test scripts are open source on GitHub.

Related categories