MCP server
Tavily MCP server
Tavily's official MCP server gives AI web search, content extraction, site mapping and crawling, all built for AI use.
- Official server
- Search and web
At a glance
- Maintained by
- Tavily
- Tools exposed
- 4 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Tavily is a search API built for AI agents. Its official MCP server offers four tools: search the web, extract the content of specific pages, map the structure of a website and crawl a site to collect its pages. Together they cover most research and data-gathering needs without running a browser yourself.
Mapping and crawling are especially useful for business tasks such as reviewing a competitor's whole product range or collecting every article from a knowledge site you are allowed to use.
It needs a Tavily API key, passed as a setting or in the hosted server address. All tools read from the web. Crawling can collect a lot of content quickly, so respect each site's terms and robots rules, and prefer an official API or data export when one exists.
We use extraction and crawling in a controlled way: a fixed list of sites, a limit on pages per run and a review of what was collected before it feeds any automated decision.
Use cases
Best business use cases
Research
Page extraction
Site mapping
Knowledge collection
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read-only web search, extraction and crawling.
-
tavily-searchReal-time web search.
-
tavily-extractExtracts content from web pages.
-
tavily-mapBuilds a structured map of a website.
-
tavily-crawlCrawls a website page by page.
Workflows
Example workflows
Website migration audit
-
1
Map your current website.
-
2
The assistant lists all sections and pages.
-
3
It flags thin or duplicate pages.
-
4
It drafts a redirect plan.
-
5
The team reviews before the move.
Competitor product review
-
1
Choose competitor sites.
-
2
Crawl their product sections with a page limit.
-
3
Extract names, prices and features.
-
4
Compare with your own range.
-
5
Review the summary with the product team.
Prompts
Example prompts
“Map the structure of our website and list pages with fewer than 200 words.”
“Extract the pricing tables from these three pages.”
“Search for recent changes to EU invoicing rules and summarize them with sources.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"tavily-mcp": {
"command": "npx",
"args": [
"-y",
"tavily-mcp@latest"
],
"env": {
"TAVILY_API_KEY": "your-api-key-here"
}
}
}
}Claude Code: terminal
claude mcp add --transport http tavily https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>- Hosted server: https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key> (or https://mcp.tavily.com/mcp with OAuth).
- Local server: stdio. npm: tavily-mcp (npx -y tavily-mcp@latest).
- Needs: TAVILY_API_KEY (or tavilyApiKey URL param for the remote server).
Security
Security considerations
-
Untrusted content
Web pages can contain text written to mislead an AI. Treat results as data, not instructions.
-
Protect the API key
Store the key outside version control and rotate it if it leaks.
-
Watch usage
Searches are billed or rate limited. Set limits and monitor use.
-
Check sources
Ask for sources and check a sample of answers by hand.
Related servers
Servers that pair well with it
Exa
Exa's official hosted MCP server gives AI search built for AI use, page fetching, advanced filters and a research agent.
Firecrawl
Firecrawl's official MCP server lets AI scrape, map, crawl and search the web and get clean, AI-ready content back.
Brave Search
Brave's official MCP server gives AI live web, news, image, video and local search from Brave's own independent index.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- AI agents AI that takes actions in your systems, such as qualifying leads or processing requests, with people checking the results.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
- Website speed optimization Find what makes a site slow and fix it, so pages load quickly on phones and rank better in search.
Solutions
View all solutions- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Price monitoring Collect competitor prices automatically, match them to your products and alert you when something changes.
- AI lead qualification Score, research and route every new inquiry so your team talks to the best leads first.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
Industries
View all industriesGuides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Astra OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use and research.
- DeepSeek V4 Pro DeepSeek's model for demanding reasoning and agent work, with thinking effort levels, tool calling, JSON output and a 1 million token window.
- Grok 4.7 xAI's current flagship for coding, agent tasks and knowledge work, with image input, tool calling, structured outputs, reasoning effort levels and a 500K window.
- Reasoning Models that think through multi-step problems before answering: analysis, planning, math, complex documents and agent work.
Glossary terms
View all glossary terms- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
- Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.
- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is maintained by Tavily.
It can extract page content, map a site's structure and crawl a site.
Only where the site's terms allow it. Prefer official APIs or exports when available.