4o-mini-search

Provides a lightweight MCP server to search the web via OpenAI's 4o-mini-search model, delivering fresh results to your AI coder.

javascript

2

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rebers-4o-mini-search-mcp": {
      "command": "npx",
      "args": [
        "@rebers/4o-mini-search-mcp"
      ],
      "env": {
        "API_KEY": "YOUR_API_KEY",
        "PROVIDER": "openai"
      }
    }
  }
}

This MCP Server lets your AI coder search the web using OpenAI’s 4o-mini Search model. It delivers fresh information directly to your AI’s context, helping you read docs, save on credits, and work with popular MCP clients out of the box.

How to use

After you configure this MCP server in your MCP client, you can ask your AI to perform web searches and retrieve current information. Examples include asking for the latest model details, explanations of framework features, or current templates. The server handles the search via the 4o-mini-search model and returns results that your AI can use in its reasoning and responses.

How to install

Prerequisites you need before setup: Node.js installed on your machine or environment, and access to an MCP client that supports stdio MCP servers.

Prepare your MCP JSON config file for your AI coder and insert the MCP server block shown below.
Save the JSON configuration and restart your MCP client so it picks up the new server.
Ensure your API key is ready for the server to use.
If you plan to use a provider other than OpenAI, set the PROVIDER value accordingly.
Begin issuing search prompts to your AI and let it fetch fresh web results via the integrated search capability.

Configuration example

{
  "mcpServers": {
    "4o-mini-search": {
      "command": "npx",
      "args": ["@rebers/4o-mini-search-mcp"],
      "env": {
        "API_KEY": "YOUR_API_KEY",
        "PROVIDER": "openai"
      }
    }
  }
}

Security and notes

Keep your API key secure. Do not share the key in public configurations and rotate it if you suspect it may be exposed. The server is designed to work with OpenAI’s 4o-mini-search model and supports OpenAI or OpenRouter as providers.

Troubleshooting

If you encounter a connection issue with your MCP client, verify the API key value in the environment variables and restart the MCP client entirely. If problems persist, ensure the MCP server configuration block is correctly added to your JSON file and that the MCP client is compatible with stdio servers.