📌Overview

Purpose: To enable AI assistants to perform web searches during user interactions, providing immediate and relevant information not present in their training data.

Overview: The OpenAI WebSearch MCP Server accesses OpenAI's websearch capabilities via the Model Context Protocol. It is designed for integration with tools like Claude.app and Zed editor, allowing for real-time information retrieval during conversations.

Key Features:

• Web Search Tool: Facilitates web searches from within conversations, offering fresh and relevant data by allowing configuration of search parameters such as context size and user location.

• Easy Installation: Provides a straightforward one-click installation process and configuration options, compatible with various environments including uvx and pip.

---

OpenAI WebSearch MCP Server

This MCP server provides access to OpenAI's websearch functionality through the Model Context Protocol. It enables AI assistants to search the web during conversations, providing up-to-date information beyond their training data. The server can be installed and configured for use with Claude.app or Zed editor.

One-Click Installation & Configuration

Claude

You can auto-update the configuration file with this recommended command:

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

Replace sk-xxxx with your OpenAI API key, available on OpenAI's platform.

Cursor

Coming soon.

Windsurf

Coming soon.

Available Tools

• web_search - Calls OpenAI websearch as a tool with the following arguments:
  • type (string): web_search_preview
  • search_context_size (string): Level of context window space for the search; one of low, medium, or high. Default is medium.
  • user_location (object or null), with fields:
    • type (string): Type of location, always approximate.
    • city (string): City of the user (e.g., San Francisco).
    • country (string): Two-letter ISO country code (e.g., US).
    • region (string): Region of the user (e.g., California).
    • timezone (string): IANA timezone (e.g., America/Los_Angeles).

Manual Installation and Configuration

Ensure uvx is installed before proceeding.

Claude Settings

1. Using uvx:

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

2. Using pip installation:

• Install the package:

pip install openai-websearch-mcp

• Modify Claude settings:

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

Configure for Zed

Add to your 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 installation:

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

Debugging

Use the MCP inspector to debug the server (for uvx installations):

npx @modelcontextprotocol/inspector uvx openai-websearch-mcp