{"type":"mcp_server","name":"mcp-tavily","description":"The Tavily MCP Server provides AI-powered web search capabilities for LLMs using Tavily's API, enabling sophisticated searches, direct answers, and recent news retrieval with AI-extracted content. The Tavily MCP Server","category":"Search & Knowledge","language":"Python","stars":72,"forks":5,"owner":"RamXX","github_url":"https://github.com/RamXX/mcp-tavily","homepage":null,"setup":"## Setup\n\n**Prerequisites:**\n- Python 3.11 or later\n- A Tavily API key\n- `uv` Python package manager (recommended)\n\n**Installation:**\n\n**Option 1: Using pip or uv**\n\n```bash\n# With pip\npip install mcp-tavily\n\n# Or with uv (recommended)\nuv add mcp-tavily\n```\n\n**Option 2: From source**\n\n```bash\n# Clone the repository\ngit clone https://github.com/RamXX/mcp-tavily.git\ncd mcp-tavily\n\n# Create a virtual environment (optional but recommended)\npython -m venv .venv\nsource .venv/bin/activate  # On Windows: .venv\\Scripts\\activate\n\n# Install dependencies and build\nuv sync  # Or: pip install -r requirements.txt\nuv build  # Or: pip install -e .\n\n# To install with test dependencies:\nuv sync --dev  # Or: pip install -r requirements-dev.txt\n```\n\n**API Key Setup:**\nThe server requires a Tavily API key, which can be provided in three ways:\n\n1.  Through a `.env` file in your project directory:\n    ```\n    TAVILY_API_KEY=your_api_key_here\n    ```\n2.  As an environment variable:\n    ```bash\n    export TAVILY_API_KEY=your_api_key_here\n    ```\n3.  As a command-line argument:\n    ```bash\n    python -m mcp_server_tavily --api-key=your_api_key_here\n    ```\n\n**Configure for Claude.app**\n\nAdd to your Claude settings:\n\n```json\n\"mcpServers\": {\n  \"tavily\": {\n    \"command\": \"python\",\n    \"args\": [\"-m\", \"mcp_server_tavily\"]\n  },\n  \"env\": {\n    \"TAVILY_API_KEY\": \"your_api_key_here\"\n  }\n}\n```\n\nIf you encounter issues, you may need to specify the full path to your Python interpreter.","tools":"## Available Tools\n\n1.  `tavily_web_search` - Performs comprehensive web searches with AI-powered content extraction.\n2.  `tavily_answer_search` - Performs web searches and generates direct answers with supporting evidence.\n3.  `tavily_news_search` - Searches recent news articles with publication dates.\n4.  **tavily_web_search** - Search the web using Tavily's AI-powered search engine (prompt template).\n5.  **tavily_answer_search** - Search the web and get an AI-generated answer with supporting evidence (prompt template).\n6.  **tavily_news_search** - Search recent news articles with Tavily's news search (prompt template).","faq":null,"created_at":"2024-12-01T18:34:28+00:00","updated_at":"2025-03-26T12:19:39+00:00","source_url":"https://model-context-protocol.com/servers/mcp-server-tavily-api-ai-search","related_articles":[]}