openai-websearch MCP Server

Use This MCP server To

Enable AI assistants to perform live web searches during conversations Provide up-to-date information beyond AI training data Integrate web search functionality into Claude.app workflows Configure web search tools for Zed editor environments Use web search results to improve AI response accuracy Automate retrieval of current events and news in chatbots Enhance AI-driven research with real-time web data Support multi-step reasoning with live web context

README

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

openai-websearch-mcp FAQ

How do I install the openai-websearch-mcp server?

You can install it using the provided one-click command with your OpenAI API key, e.g., `OPENAI_API_KEY=sk-xxxx uv run --with uv --with openai-websearch-mcp openai-websearch-mcp-install`.

Can I use this MCP server with platforms other than Claude.app?

Currently, it supports Claude.app and Zed editor, with plans to support Cursor and Windsurf soon.

What API key do I need to use this server?

You need an OpenAI API key, which you can obtain from OpenAI's platform. This key enables access to the web search functionality.

Does this server support other LLM providers besides OpenAI?

While this server specifically uses OpenAI's web search API, it can be integrated into environments that also use models from Claude and Gemini.

What is the 'web_search' tool provided by this server?

The 'web_search' tool allows the MCP client to call OpenAI's web search API with parameters like 'type' and 'search_context_size' to retrieve relevant web results.

How does this server improve AI assistant responses?

By enabling real-time web searches, it provides current and relevant information that may not be in the AI's training data, improving accuracy and relevance.

Is the configuration process automated?

Yes, the recommended installation command can automatically update the configuration file with your API key and settings.

Are there plans to support more platforms?

Yes, support for Cursor and Windsurf platforms is coming soon.