Openai WebSearch

🚀 OpenAI Web Search MCP Server

This MCP server provides access to OpenAI's web search functionality through the Model Context Protocol. It enables AI assistants to conduct web searches during conversations with users, offering up - to - date information that may not be in the assistant's training data. This server can be installed and configured for Claude.app or Zed Editor.

🚀 Quick Start

One - Click Installation and Configuration

Claude

!! Can this command automatically update the configuration file? (Recommended)

OPENAI_API_KEY=sk-xxxx uv run --with uv --with openai-websearch-mcp openai-websearch-mcp-install

sk-xxxx is your API key. You can obtain it from OpenAI's platform.

Cursor

Coming soon.

Windsurf

Coming soon.

✨ Features

Available Tools

• web_search - Invoke OpenAI web search as a tool.
  • Required parameters:
    • type (string): web_search_preview
    • search_context_size (string): High - level guidance on the size of the context window. Can be low, medium, or high, where medium is the default.
    • user_location (object or null)
      • type (string): The type of user location. Always approximate.
      • city (string): Free - text input of the user's city, e.g., San Francisco.
      • country (string): Two - letter ISO country code of the user, e.g., US.
      • region (string): Free - text input of the user's region, e.g., California.
      • timezone (string): IANA timezone of the user, e.g., America/Los_Angeles.

📦 Installation

Manual Installation and Configuration

Please ensure that uvx is installed before proceeding.

Add the following to your Claude settings:

Using uvx

"mcpServers": {
  "openai-websearch-mcp": {
    "command": "uvx",
    "args": ["openai-websearch-mcp"],
    "env": {
        "OPENAI_API_KEY": "your-api-key-here"
    }
  }
}

Using pip

1. Install openai-websearch-mcp via pip:

pip install openai-websearch-mcp

2. Modify your Claude settings:

"mcpServers": {
  "openai-websearch-mcp": {
    "command": "python",
    "args": ["-m", "openai_websearch_mcp"],
    "env": {
        "OPENAI_API_KEY": "your-api-key-here"
    }
  }
}

Configure Zed

Add the following to your Zed settings.json:

Using uvx

"context_servers": [
  "openai-websearch-mcp": {
    "command": "uvx",
    "args": ["openai-websearch-mcp"],
    "env": {
        "OPENAI_API_KEY": "your-api-key-here"
    }
  }
],

Using pip

"context_servers": {
  "openai-websearch-mcp": {
    "command": "python",
    "args": ["-m", "openai_websearch_mcp"],
    "env": {
        "OPENAI_API_KEY": "your-api-key-here"
    }
  }
},

🔧 Technical Details

Debugging

You can use the MCP inspector to debug the server. For uvx installations:

npx @modelcontextprotocol/inspector uvx openai-websearch-mcp