Tavily MCP Server implementation that uses fastmcp and supports both **sse** and **stdio** transports. To use this server, you need a Tavily account
Tavily mcp sse mcp server connects Tavily MCP Sse to AI assistants that speak the Model Context Protocol. Tavily MCP Server implementation that uses fastmcp and supports both sse and stdio transports. To use this server, you need a Tavily account and a Tavily API key, which must be loaded into the TAVILY_API_KEY environment variable.
Tavily MCP Server implementation that uses fastmcp and supports both sse and stdio transports. To use this server, you need a Tavily account and a Tavily API key, which must be loaded into the TAVILY_API_KEY environment variable.
Once connected, the assistant can call this tool directly:
Real — time web search capabilities through the tavily-search toolSetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply one environment variable: TAVILY_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.
Search and scraping servers exist to fix the single most common failure of any assistant: answering from stale training data instead of what is on the web today. Tavily MCP Sse sits in that group, and the shape of its toolset — Real — tells you what it is really for. Worth comparing against the other search web scraping servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Real | time web search capabilities through the tavily-search tool |
# Running on STDIO
```json
{
"mcpServers": {
"tavily-mcp-server": {
"command": "uv",
"args": [
"run",
"--directory",
"<LOCATION-TO-THE-REPO>",
"tavily-mcp-stdio"
],
"env": {
"TAVILY_API_KEY": "<YOUR-API-KEY>"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| TAVILY_API_KEY | Credential the server authenticates with. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.