OpenAI WebSearch MCP

What is openai-websearch-mcp?

openai-websearch-mcp is a Python-based Model Context Protocol (MCP) server that allows AI assistants to utilize OpenAI's web_search tool. This enables AI models to perform real-time web searches during conversations, providing them with current information beyond their training data.

How to use openai-websearch-mcp?

There are two primary methods for installing and configuring openai-websearch-mcp:

One-click Installation & Configuration (Recommended)

For Claude.app, you can use the following command, which also auto-updates the configuration file:

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

Replace sk-xxxx with your actual OpenAI API key.

Manual Installation and Configuration

1. Using uvx:

Ensure uvx is installed. Then, add the following to your Claude settings (e.g., settings.json):

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

For Zed editor, add to your settings.json:

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

2. Using pip installation:

First, install the package via pip:

pip install openai-websearch-mcp

Then, modify your Claude settings:

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

For Zed editor, modify your settings.json:

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

Key Features of openai-websearch-mcp

• OpenAI Web Search Integration: Provides seamless access to OpenAI's web_search tool.
• Model Context Protocol (MCP) Server: Functions as an MCP server, allowing AI assistants to interact with the web search functionality.
• Configurable Web Search Parameters: Supports search_context_size (low, medium, high) and user_location (city, country, region, timezone) for refined search results.
• Easy Installation: Offers both one-click and manual installation options for flexibility.
• Compatibility: Designed for use with AI assistants like Claude.app and Zed editor.

Use Cases of openai-websearch-mcp

• Real-time Information Retrieval: AI assistants can fetch the latest information from the web during conversations, ensuring up-to-date responses.
• Enhanced Conversational AI: Improves the utility and accuracy of AI assistants by giving them access to external knowledge.
• Dynamic Content Generation: Enables AI to generate responses based on current events or rapidly changing data.
• Research and Inquiry: AI assistants can perform web searches to answer user queries that require external data.

FAQ from openai-websearch-mcp

Q: What is the OPENAI_API_KEY and where can I get it?

A: The OPENAI_API_KEY is your authentication key for accessing OpenAI's services. You can obtain it from OpenAI's platform.

Q: How can I debug the openai-websearch-mcp server?

A: For uvx installations, you can use the MCP inspector:

npx @modelcontextprotocol/inspector uvx openai-websearch-mcp

Q: Are there plans for integration with other AI tools like Cursor and Windsurf?

A: Yes, the README indicates that integration with Cursor and Windsurf is "Coming soon."

Q: What are the required arguments for the web_search tool?

A: The required arguments are type (always web_search_preview) and search_context_size (low, medium, or high). Optionally, user_location can be provided with details like city, country, region, and timezone.

OpenAI WebSearch MCP Server

This MCP server provides access to OpenAI's websearch functionality through the Model Context Protocol. It allows AI assistants to search the web during conversations with users, providing up-to-date information that may not be available in the assistant's training data. The server can be installed and configured for use with Claude.app or Zed editor.

One click installation & Configuration

Claude

!!Can using this command auto update configure file（Recommend）

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 get it from openai's open platform

Cursor

Conming soon

Windsurf

Conming soon

Available Tools

• web_search - Call openai websearch as tool.
  • Required arguments:
    • type (string): web_search_preview
    • search_context_size (string): High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
    • user_location (object or null)
      • type (string): The type of location > approximation. Always approximate.
      • city (string): Free text input for the city of the user, e.g. San Francisco.
      • country (string): The two-letter ISO country code of the user, e.g. US.
      • region (string): Free text input for the region of the user, e.g. California.
      • timezone (string): The IANA timezone of the user, e.g. America/Los_Angeles.

Manual installation and configuration

Please make sure uvx is installed before installation

Add to your 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

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 for Zed

Add 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 installation

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

Debugging

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

npx @modelcontextprotocol/inspector uvx openai-websearch-mcp