# Tavily (MCP Server)

> Real-time web search, extraction, site mapping and crawling for agents

- Type: MCP server
- Publisher: Tavily (official)
- Categories: Research, AI & ML
- Website: https://docs.tavily.com/documentation/mcp
- Docs: https://docs.tavily.com/documentation/mcp
- Source: https://github.com/tavily-ai/tavily-mcp
- Transport: streamable-http
- Server URL: https://mcp.tavily.com/mcp/
- Launch command: npx -y tavily-mcp@latest
- Sign-in: api-key
- Environment variables: TAVILY_API_KEY
- GitHub stars: 2415
- Listed: 2025-01-27

## About

Tavily's official MCP server exposes its search, extract, map and crawl APIs to AI assistants. It can be used as a hosted remote server (API key in URL or OAuth) or run locally via npx with a TAVILY_API_KEY.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.tavily.com/mcp/ as the MCP server URL. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add tavily --url https://mcp.tavily.com/mcp/ --bearer-token-env-var TAVILY_API_KEY
   ```

   config.toml:

   ```toml
   [mcp_servers.tavily]
   url = "https://mcp.tavily.com/mcp/"
   bearer_token_env_var = "TAVILY_API_KEY"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "tavily",
           "server_url": "https://mcp.tavily.com/mcp/",
           "authorization": os.environ["TAVILY_API_KEY"],
           "require_approval": "never",
       }],
       input="Search for today's news about the EU AI Act",
   )
   print(response.output_text)
   ```

## Tools

- `tavily-search`
- `tavily-extract`
- `tavily-map`
- `tavily-crawl`

## Example prompts

- "Search for today's news about the EU AI Act"
- "Extract the main content from these three URLs"
- "Map all pages under docs.example.com"
- "Crawl this blog and summarize posts about pricing"

## Also available as

- app: [Tavily](https://chatgptplugins.directory/apps/tavily.md)

## Related

- [Browser Use](https://chatgptplugins.directory/mcp/browser-use.md): Run Browser Use cloud browser agents or control a local browser over MCP
- [Memory](https://chatgptplugins.directory/mcp/memory.md): Knowledge graph-based persistent memory across conversations
- [Mem0](https://chatgptplugins.directory/mcp/mem0.md): Hosted long-term memory for AI agents and clients
- [Sequential Thinking](https://chatgptplugins.directory/mcp/sequential-thinking.md): Structured, reflective step-by-step problem solving for LLMs
- [Fetch](https://chatgptplugins.directory/mcp/fetch.md): Fetch web pages and convert them to markdown for LLMs
- [Serena](https://chatgptplugins.directory/mcp/serena.md): Semantic code retrieval and editing toolkit for coding agents

---
Source: https://chatgptplugins.directory/mcp/tavily · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.