Model Context Protocol moderate risk

OpenAI Websearch

Provides intelligent web search capabilities using OpenAI's reasoning models, ideal for AI assistants needing up-to-date information.

Connections & Capabilities

Connects To

GitHub

Capabilities

read

Quickstart

Install

pip install openai-websearch-mcp

Config

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

Exposed MCP Tools (1)

safe

openai_web_search

Performs intelligent web searches using OpenAI's reasoning models.

Primarily a read-only operation, retrieving information from the web.

Safety Assessment

The server is relatively safe for read-only operations, but the dependency on an external API and the potential for unpredictable model outputs introduce moderate risks. It is safe to use with proper API key management and monitoring of query content. Risky scenarios include using a compromised API key or performing sensitive queries without adequate safeguards.

Requires an OpenAI API key for access, limiting unauthorized use.
Primarily performs read operations (web searches).
Reasoning effort can be adjusted to control resource consumption.
No direct filesystem access or shell execution capabilities.
Limited write capabilities

Relies on external OpenAI API, introducing a dependency and potential point of failure.
Misconfigured or compromised API key could lead to unauthorized usage and cost implications.
Reasoning models can produce unpredictable outputs, requiring careful monitoring.
Potential for information leakage if sensitive queries are performed.
Exposure to external web content carries inherent risks of malicious content.