Spark
Sign In
MCP Connector

Perform Intelligent Web Searches with OpenAI

MCP server providing web search capabilities using OpenAI reasoning models, with support for GPT-5 series and smart effort control.

Connect
Works with openai
ConechoAI
Own this? Claim it

Maintainer of this project? Claim this page to edit the listing.

90
Spark score
out of 100
Updated 5 months ago
Version 1.0.0
Models
gpt 4o
Add to Favorites

Why it matters

Leverage advanced OpenAI reasoning models to conduct intelligent web searches, providing comprehensive analysis and summaries for various use cases.

Outcomes

What it gets done

01

Execute web searches using OpenAI's latest GPT-5 series and other compatible models.

02

Customize search effort for fast iterations or deep research.

03

Integrate location-based search parameters for targeted results.

04

Debug search operations with provided tools.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-openai-websearch-mcp | bash

Capabilities

Tools your agent gets

openai_web_search

Intelligent web search with reasoning model support and customizable parameters for query input and model selection.

Overview

OpenAI WebSearch MCP Server

This MCP server offers web search functionality powered by OpenAI's reasoning models. It supports the GPT-5 series and includes features for smart effort control, enabling multi-mode searches for fast iterations or deep research. The server also allows for location-based search customization and provides comprehensive parameter documentation. This connector is suitable for users who need to integrate intelligent web search capabilities into their AI agents or applications, leveraging OpenAI's advanced models for data retrieval and analysis. It is particularly useful for tasks requiring nuanced understanding of search results, such as comprehensive analysis of complex topics or finding localized information.

What it does

An advanced MCP server that provides intelligent web search capabilities using OpenAI's reasoning models, with support for the latest GPT-5 series and smart effort control for various use cases.

Installation can be done via uvx:

uvx openai-websearch-mcp

Or via pip:

pip install openai-websearch-mcp
python -m openai_websearch_mcp

Configuration for tools like Claude Desktop or Cursor:

{
  "mcpServers": {
    "openai-websearch-mcp": {
      "command": "uvx",
      "args": ["openai-websearch-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here",
        "OPENAI_DEFAULT_MODEL": "gpt-5-mini"
      }
    }
  }
}
Source README

An advanced MCP server that provides intelligent web search capabilities using OpenAI's reasoning models, with support for the latest GPT-5 series and smart effort control for various use cases.

Installation

One-Click Installation

OPENAI_API_KEY=sk-xxxx uvx --with openai-websearch-mcp openai-websearch-mcp-install

uvx (Recommended)

### Install and run directly
uvx openai-websearch-mcp

### Or install globally
uvx install openai-websearch-mcp

pip

### Install from PyPI
pip install openai-websearch-mcp

### Run the server
python -m openai_websearch_mcp

From Source

### Clone the repository
git clone https://github.com/yourusername/openai-websearch-mcp.git
cd openai-websearch-mcp

### Install dependencies
uv sync

### Run in development mode
uv run python -m openai_websearch_mcp

Configuration

Claude Desktop

{
  "mcpServers": {
    "openai-websearch-mcp": {
      "command": "uvx",
      "args": ["openai-websearch-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here",
        "OPENAI_DEFAULT_MODEL": "gpt-5-mini"
      }
    }
  }
}

Cursor

{
  "mcpServers": {
    "openai-websearch-mcp": {
      "command": "uvx",
      "args": ["openai-websearch-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here",
        "OPENAI_DEFAULT_MODEL": "gpt-5-mini"
      }
    }
  }
}

Local Development

{
  "mcpServers": {
    "openai-websearch-mcp": {
      "command": "/path/to/your/project/.venv/bin/python",
      "args": ["-m", "openai_websearch_mcp"],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here",
        "OPENAI_DEFAULT_MODEL": "gpt-5-mini",
        "PYTHONPATH": "/path/to/your/project/src"
      }
    }
  }
}

Available Tools

Tool Description
openai_web_search Intelligent web search with reasoning model support, supporting parameters for query input, model...

Features

  • Full compatibility with the latest OpenAI reasoning models (gpt-5, gpt-5-mini, gpt-5-nano, o3, o4-mini)
  • Intelligent default values for reasoning_effort based on use case
  • Multi-mode search: fast iterations with gpt-5-mini or deep research with gpt-5
  • Support for location-based search customization
  • Complete parameter documentation for easy integration
  • Environment variable support for straightforward deployment

Environment Variables

Required

  • OPENAI_API_KEY - Your OpenAI API key

Optional

  • OPENAI_DEFAULT_MODEL - Default model to use

Usage Examples

Find the latest developments in AI reasoning models using openai_web_search

Use openai_web_search with gpt-5 and high reasoning effort to provide comprehensive analysis of breakthroughs in quantum computing

Find local tech meetups in San Francisco this week using openai_web_search

Resources

Notes

Supports both fast searches with gpt-5-mini for quick iterations and deep research with gpt-5 for comprehensive analysis. The server automatically handles compatibility by applying reasoning parameters only to compatible models. Use the MCP Inspector for debugging: npx @modelcontextprotocol/inspector uvx openai-websearch-mcp

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.