Set it up
- 1
Turn on Tavily in your AI
In Claude: open Settings → Connectors and add Tavily. In ChatGPT: Settings → Apps & Connectors.
- 2
Add it to your app once
Copy the short config below into your app. It just tells your AI where to find Tavily.
- 3
Just ask
Tell it what you want in plain words — no special commands.
For example, say
“Research the current state of WebAssembly adoption and summarize what you find”
Need the exact config? Show it +
Add to your client
{
"mcpServers": {
"tavily": {
"command": "npx",
"args": ["-y", "tavily-mcp"],
"env": {
"TAVILY_API_KEY": "<your-tavily-api-key>"
}
}
}
}Paste into your client's MCP configuration file.
Get the skill
A ready-made skill that teaches your AI agent to use Tavily well. Tavily's official search, extract, crawl and research skills.
npx skills add tavily-ai/skills Quick skills
Copy one, paste it to your AI, watch it work.
Multi-Source Research
“Research the top 5 CRM tools for small businesses and summarize their pricing and main features”
Cleaned Content Extraction
“Search for 'how to set up Postgres replication' and return the full cleaned content of the top 3 results”
Agent-Ready Search
“Before writing this report, search for the latest stats on remote work adoption in 2026”
Good to know
- · Tavily charges per search and extraction — monitor your quota
- · Results quality varies by query phrasing — vague queries return noise
- · Full-page extraction costs more than snippet-only — choose the right mode
When to use
- ✓ You're building an AI agent that needs web research as a tool
- ✓ You want search results that are cleaned and ready for LLM consumption
- ✓ You need research across multiple sources in a single call
- ✓ You want both snippets and full-page extraction options
When not to use
- × You only need one quick answer (Perplexity is more concise)
- × You need real-time prices or live data — web search is usually stale by seconds to hours
- × You're doing totally free research — Tavily is usage-based
About
Imagine asking your AI: 'Research the top 5 project management tools and compare their pricing' — and it performs multi-source web research optimized for AI consumption. This server connects your AI to Tavily's search API, which is built specifically for AI agents rather than human browsing.
The Tavily MCP server integrates Tavily's AI-optimized search engine into AI assistants. Designed specifically for LLM consumption, Tavily returns structured, relevant results with reduced noise compared to general search engines.
Popular in AI agent frameworks like LangChain and LlamaIndex. Free tier available for development.
Workflows That Use Tavily MCP
Works With
Also Consider
FAQ
What does Tavily MCP do? +
Imagine asking your AI: 'Research the top 5 project management tools and compare their pricing' — and it performs multi-source web research optimized for AI consumption. This server connects your AI to Tavily's search API, which is built specifically for AI agents rather than human browsing.
Do I need to know how to code? +
No. Turn it on in your AI's settings and ask in plain English — no terminal, no coding.
When should I use Tavily MCP? +
Reach for it when you need to: You're building an AI agent that needs web research as a tool; You want search results that are cleaned and ready for LLM consumption; You need research across multiple sources in a single call; You want both snippets and full-page extraction options.
When should I avoid Tavily MCP? +
Skip it when: You only need one quick answer (Perplexity is more concise); You need real-time prices or live data — web search is usually stale by seconds to hours; You're doing totally free research — Tavily is usage-based.
How do I install Tavily MCP? +
In Claude Code, run: claude mcp add tavily -e TAVILY_API_KEY=<your-key> -- npx -y tavily-mcp. Copy-paste configs for Claude Desktop, Cursor, and Windsurf are at the top of this page.
