OpenAI Web Search MCP Server logo

OpenAI Web Search MCP Server

by bitibi

A TypeScript implementation of an MCP server providing web search functionality using OpenAI's web search preview feature. It allows AI models to perform real-time web searches through the OpenAI API.

View on GitHub

Last updated: N/A

What is OpenAI Web Search MCP Server?

This is an MCP server that leverages OpenAI's Responses API with the web_search_preview capability to provide real-time web search functionality to AI models.

How to use OpenAI Web Search MCP Server?

Install the server using npm or npx, set your OpenAI API key as an environment variable, and configure your MCP client (e.g., Claude Desktop) to use the server. The server provides a web_search tool accessible through the MCP protocol.

Key features of OpenAI Web Search MCP Server

  • Real-time web search

  • OpenAI Responses API integration

  • MCP compatibility

  • Easy installation and setup

  • Configurable port

Use cases of OpenAI Web Search MCP Server

  • Providing up-to-date information to AI models

  • Enabling AI models to answer questions requiring web search

  • Augmenting AI model knowledge with external data

  • Supporting AI-powered research and analysis

FAQ from OpenAI Web Search MCP Server

What is an MCP server?

MCP stands for Model Context Protocol. It allows different AI models and tools to communicate with each other.

How do I get an OpenAI API key?

You can obtain an OpenAI API key by signing up for an account on the OpenAI platform.

What is the default port for the server?

The default port is 3000, but you can change it using the PORT environment variable.

Can I use this server with other MCP clients besides Claude Desktop?

Yes, any MCP client that supports configuring custom servers can be used with this server.

What kind of queries can the web search tool handle?

The web search tool can handle any query that can be used with a typical web search engine. The quality of the results depends on OpenAI's web search implementation.