Tavily Search MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Tavily Search MCP Server search for latest news on AI developments"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tavily Search MCP Server
A Model Context Protocol (MCP) server for the Tavily Search API with automatic multi-key fallback. Built with FastMCP.
Features
🔄 Multi-key auto fallback — automatically rotates through
TAVILY_API_KEY_1,TAVILY_API_KEY_2, etc. when rate-limited🌐 Web search —
tavily_searchfor general web search📄 Content extraction —
tavily_extractto get content from URLs🗺️ Crawl & Map —
tavily_crawl/tavily_mapfor website structure🔬 Deep Research —
tavily_research_create/tavily_research_getfor AI-powered research📊 Usage tracking —
tavily_usageto check API quota
Related MCP server: Tavily MCP Server
Quick Start
{
"mcpServers": {
"tavily-search": {
"command": "uvx",
"args": ["tavily-search-mcp-server"]
}
}
}Environment Variables
Variable | Required | Description |
| Yes | Primary Tavily API key |
| No | Fallback keys for auto-rotation |
The server automatically discovers TAVILY_API_KEY_* env vars and falls back through them on 429 errors. Also supports single TAVILY_API_KEY for backward compatibility.
Available Tools
Tool | Description |
| Search the web with configurable depth, topic, time range |
| Extract content from one or more URLs |
| Crawl a website with depth/breadth control |
| Map website structure |
| Search with raw content results |
| Create a deep research task |
| Get research task status/results |
| Check API usage/quota |
License
MIT
Available Tools
8 toolstavily_crawlC
爬取网站。多 API Key 自动轮换。
Inputs: url (required), max_depth, max_breadth, limit, +13 more. Returns: result
tavily_extractC
从 URL 提取内容。多 API Key 自动轮换。
Inputs: urls (required), extract_depth, include_images, format, +5 more. Returns: result
tavily_mapC
绘制网站结构地图。多 API Key 自动轮换。
Inputs: url (required), max_depth, max_breadth, limit, +9 more. Returns: result
tavily_research_createC
创建 Tavily 深度研究任务。多 API Key 自动轮换。
Inputs: input (required), model, output_schema, stream, +2 more. Returns: result
tavily_research_getC
查询 Tavily 深度研究任务状态/结果。多 API Key 自动轮换。
Inputs: request_id (required). Returns: result
tavily_searchC
搜索互联网获取最新信息。多 API Key 自动轮换,配额耗尽时自动切换。
Inputs: query (required), search_depth, topic, time_range, +15 more. Returns: result
tavily_search_contextC
搜索并返回带原始内容的上下文结果。多 API Key 自动轮换。
Inputs: query (required), search_depth, topic, days, +7 more. Returns: result
tavily_usageA
查询 Tavily 使用量/额度。多 API Key 自动轮换。
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: search, search with context, crawl, extract, map, research creation, research retrieval, and usage monitoring. No overlap or ambiguity.
All tools follow the consistent 'tavily_<verb>' pattern, using clear action verbs like search, crawl, extract, map, research_create, research_get, and usage. No mixing of conventions.
8 tools is appropriate for a web search and research service, covering core operations without being excessive or insufficient.
The tool surface covers search, crawling, extraction, site mapping, research tasks, and usage monitoring. Minor gap: no tool to list or cancel research tasks, but core workflows are covered.
Maintenance
Related MCP Connectors
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Web scraping, search, crawling, structured extraction and research for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceProvides AI-powered web search capabilities using Tavily's search API, enabling LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles.72MIT
- AlicenseNot gradedqualityDmaintenanceProvides AI assistants with real-time web search, intelligent data extraction from web pages, website mapping, and web crawling capabilities through Tavily's API. Enables comprehensive web research and content analysis through natural language interactions.19,428 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform real-time web searches, extract data from web pages, map website structures, and crawl websites using the Tavily API.85 npmMIT
- FlicenseNot gradedqualityDmaintenanceProvides web search capabilities using the Tavily API, enabling AI models to search the internet and retrieve up-to-date information.-