Tavily MCP Server
AI-optimized search engine for research and information retrieval. Structured results for AI agents.
- Maintained by
- Tavily
- Hosting
- Hosted endpoint, or run it locally
- Authentication
- OAuth sign-in
- Last checked
Remote also accepts the API key as a Bearer header or tavilyApiKey query parameter.
How to connect the Tavily MCP server
Pick your AI client and paste the snippet. Swap the YOUR_… placeholders for your own values. New to this? Our guide to how MCP clients and servers fit together explains what each piece does.
Claude Code
claude mcp add --transport http tavily https://mcp.tavily.com/mcp Then run /mcp inside Claude Code and choose Authenticate to sign in.
Full Claude Code setup guide →Claude Desktop and claude.ai
Name: Tavily
Remote MCP server URL: https://mcp.tavily.com/mcp Custom connectors need a Pro, Max, Team or Enterprise plan. On Team and Enterprise an owner adds them in admin settings.
Full Claude Desktop setup guide →Cursor
{
"mcpServers": {
"tavily": {
"url": "https://mcp.tavily.com/mcp"
}
}
} VS Code
{
"servers": {
"tavily": {
"type": "http",
"url": "https://mcp.tavily.com/mcp"
}
}
} ChatGPT
Business, Enterprise and Edu plans (and Pro, read-only) can add this endpoint as an app in developer mode. ChatGPT setup guide →
+ − Run it locally instead
Claude Code
claude mcp add --env TAVILY_API_KEY=YOUR_API_KEY --transport stdio tavily \
-- npx -y tavily-mcp@latest Claude Desktop
{
"mcpServers": {
"tavily": {
"command": "npx",
"args": [
"-y",
"tavily-mcp@latest"
],
"env": {
"TAVILY_API_KEY": "YOUR_API_KEY"
}
}
}
} Fully quit and reopen Claude Desktop after saving.
Full Claude Desktop setup guide →Cursor
{
"mcpServers": {
"tavily": {
"command": "npx",
"args": [
"-y",
"tavily-mcp@latest"
],
"env": {
"TAVILY_API_KEY": "YOUR_API_KEY"
}
}
}
} VS Code
{
"servers": {
"tavily": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tavily-mcp@latest"
],
"env": {
"TAVILY_API_KEY": "YOUR_API_KEY"
}
}
}
} Frequently asked questions
What is the Tavily MCP server?
It is a Model Context Protocol (MCP) server — a small piece of software that gives AI assistants like Claude a secure, governed connection to Tavily. AI-optimized search engine for research and information retrieval. Structured results for AI agents.
Is there an official Tavily MCP server?
Yes. The Tavily MCP server is an official integration, maintained by the vendor or the Model Context Protocol project, which makes it the safest default for business use. It is maintained by Tavily.
Is the Tavily MCP server hosted, or do I run it myself?
Both. Tavily runs a hosted endpoint at https://mcp.tavily.com/mcp, so most people just paste that URL into their AI client. You can also run the server locally with npx, supplying your own credentials.
Do I need an API key for the Tavily MCP server?
No API key is needed for the hosted server. You sign in through Tavily's own OAuth screen, and the assistant only gets the access your account has.
What can an AI assistant actually do with Tavily?
Through this server an assistant can work with search, research, content extraction, structured results — reading from and acting on Tavily directly instead of you copy-pasting between windows. What you allow it to do is controlled by the permissions you grant.
How do I set this up for my business?
The setup section above has copy-paste config for Claude Code, Claude Desktop, Cursor and VS Code. If you want it rolled out across a team with permissions, governance and support handled, that is what Crox's Build engagement covers.
New to MCP? Start with our plain-English guide to the Model Context Protocol or see how to connect AI to your business tools without writing code .
Want this connected to your business — with governance handled?
Crox maps your processes, connects AI to the tools you already use, and keeps it working as models change. Start with a readiness assessment or talk to us about a build.