A production-ready MCP (Model Context Protocol) server that provides web search capabilities using the Tavily API. This server integrates seamlessly with Roo and other MCP-compatible AI assistants.
tavily-mcp-server is an MCP project maintained in the altinakseven/tavily-mcp-server repository. The maintainer describes its purpose as “A production-ready MCP (Model Context Protocol) server that provides web search capabilities using the Tavily API. This server integrates seamlessly with Roo and other MCP-compatible…”. Read the project documentation for the complete scope.
The project provides a local client configuration using node. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.
The example declares TAVILY_API_KEY. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"tavily-search": {
"command": "node",
"args": [
"/home/ubuntu/roo-tavily/tavily-mcp-server/dist/index.js"
],
"env": {
"TAVILY_API_KEY": "YOUR_TAVILY_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| TAVILY_API_KEY | Declared in the maintainer’s client configuration. | Yes |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Public MCP server for the LLM Search Engine
This project implements a Model Context Protocol (MCP) server for Brave Search, allowing integration with AI assistants like Claude.
MCP server for action governance on AI agents — 14 tools that govern tool calls, SQL queries, file writes, shell commands, and agent-to-agent
Token compression for web content — 70-80% reduction from HTML to clean markdown