OpenAI-WebSearch-MCP-Server

OpenAI-WebSearch-MCP-Server

3.4

OpenAI Web Search MCP Server is a TypeScript-based server that enables real-time web search functionality using OpenAI's web search preview feature.

The OpenAI Web Search MCP Server is a TypeScript implementation designed to provide web search capabilities through OpenAI's Responses API with the `web_search_preview` feature. This server allows AI models to perform real-time web searches, offering up-to-date information from the internet. It is particularly useful for applications that require dynamic data retrieval and integration with MCP clients. The server can be easily installed and configured, supporting both direct execution and global installation. It is designed to work seamlessly with various MCP clients, such as Claude Desktop, by providing a straightforward setup process.

Features

  • Real-time web search using OpenAI's Responses API.
  • Easy installation and setup with npx or npm.
  • Configurable environment variables for API key and port.
  • Seamless integration with MCP clients like Claude Desktop.
  • Development and build scripts for customization and deployment.

Tools

  1. web_search

    Accept query string as input and perform real-time web search using OpenAI's web_search_preview function