OpenAI Web Search MCP Server

@bitibi

Basic information

About OpenAI Web Search MCP Server

A server for handling OpenAI web search using MCP (Multi-Config Protocol)

OpenAI Web Search MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "OpenAI-WebSearch-MCP-Server": {
      "command": "npx",
      "args": [
        "openai-websearch-mcp-server"
      ]
    }
  }
}

OpenAI Web Search MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is OpenAI Web Search MCP Server?

A TypeScript‑based MCP server that lets AI models perform real‑time web searches through the OpenAI API, using the Responses API’s web_search_preview feature. It is built for developers who want to add live web search capabilities to any MCP‑compatible client (e.g., Claude Desktop).

How to use OpenAI Web Search MCP Server?

Install with npx openai-websearch-mcp-server or npm install -g openai-websearch-mcp-server, then set the OPENAI_API_KEY environment variable. Run the server with openai-websearch-mcp. Configure your MCP client to launch the server and send tool calls to the web_search tool, which accepts a query string and returns results from across the internet.

Key features of OpenAI Web Search MCP Server

Real‑time web search via OpenAI’s web_search_preview capability
Simple MCP‑compliant tool interface (web_search)
Run directly with npx or install globally
Port configurable via the PORT environment variable
Works with any MCP client (Claude Desktop, etc.)

Use cases of OpenAI Web Search MCP Server

Enabling an AI assistant to look up current news or facts
Providing up‑to‑date information to a chatbot without manual data refreshes
Adding a search tool to your custom MCP‑powered application

Frequently asked questions

What does the server do?

It exposes a `web_search` tool that uses OpenAI’s Responses API to perform live web searches, returning results directly to an MCP client.

How do I set my OpenAI API key?

Set the environment variable `OPENAI_API_KEY` before running the server: `export OPENAI_API_KEY='your-api-key-here'`.

Do I need any other services?

Only an OpenAI API key with access to the Responses API’s `web_search_preview` feature. No additional database or third‑party search engine is required.

How do I change the port?

Set the `PORT` environment variable, e.g., `PORT=8080 openai-websearch-mcp`. The default port is 3000.

How is this server intended to be used?

It is designed to be launched by an MCP client (like Claude Desktop) via the command line, with the API key provided in the client configuration’s environment.

Comments

More AI & Agents MCP servers

Factanker

FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil

Cartesia MCP

cartesia-ai

Cartesia MCP is a remote MCP server for Cartesia (https://cartesia.ai) available at https://mcp.cartesia.ai.

q-ring

I4cTime

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.

AskOne: Live Q&A and Polls

phuryn

Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the resu

GoBuy - Product Trust

gobuy-ai

GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,