This Tavily Search MCP server, developed by Alexandros Pappas, integrates the Tavily Search API into the Model Context Protocol framework. Built with TypeScript and leveraging Express.js, it provides a streamlined interface for AI models to perform web searches using Tavily's advanced search capabilities. The implementation supports both stdio and Server-Sent Events (SSE) communication methods, making it versatile for different deployment scenarios. It's particularly useful for enhancing AI-driven applications with real-time, high-quality web search results, enabling use cases like fact-checking, research assistance, or content generation that requires up-to-date information from the internet.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIExecute web searches using the Tavily Search API. Inputs: query (string, required), search_depth (string, optional: 'basic' or 'advanced', default: 'basic'), topic (string, optional: 'general' or 'news', default: 'general'), days (number, optional: Number of days back for news search, default: 3), time_range (string, optional: Time range filter: 'day', 'week', 'month', 'year' or 'd', 'w', 'm', 'y'), max_results (number, optional: Maximum number of results, default: 5), include_images (boolean, optional: Include related images, default: false), include_image_descriptions (boolean, optional: Include descriptions for images, default: false), include_answer (boolean, optional: Include a short LLM-generated answer, default: false), include_raw_content (boolean, optional: Include raw HTML content, default: false), include_domains (string[], optional: Domains to include), exclude_domains (string[], optional: Domains to exclude).
