Web_Search_MCP

by memohib

AI/Development Tools Web Search Tavily API Langchain

Web_Search_MCP is an MCP server providing a web search tool. It integrates the Tavily API with MCP to enable real-time web search capabilities for AI systems.

View on GitHub

Last updated: N/A

What is Web_Search_MCP?

Web_Search_MCP is an MCP (Model Context Protocol) server that provides a web search tool. It allows AI systems to access real-time web search results via the Tavily API.

How to use Web_Search_MCP?

First, configure the .env file with your Tavily API key. Then, install the dependencies using uv add "mcp[cli]" python-dotenv langchain-community tavily-python. Finally, run the server using the Claude desktop application or directly using uv run main.py after activating the virtual environment.

Key features of Web_Search_MCP

Real-time web search using Tavily API
Integration with MCP for AI systems
Detailed search results with content, URL, and relevancy score
JSON formatted output
Asynchronous processing
Error handling

Use cases of Web_Search_MCP

Providing real-time information to language models
Enhancing AI applications with web search capabilities
Automated research and data gathering
Contextualizing AI responses with up-to-date information

FAQ from Web_Search_MCP

What is the Tavily API?

The Tavily API is a search API that provides real-time, comprehensive web search results, including answers, raw content, and relevant metadata.

What is MCP?

MCP stands for Model Context Protocol, a standard for enabling communication between AI models and external tools.

How do I get a Tavily API key?

You can obtain a Tavily API key by signing up on the Tavily website.

What is the input for the `search_web` tool?

The input for the search_web tool is a string representing the search query.

What is the output of the `search_web` tool?

The output is a JSON formatted string containing the search results, including the title, URL, content, score, and raw content of each result.