# openai-websearch-mcp

> MCP Server

This repository provides an MCP server for accessing OpenAI's websearch functionality, enabling AI assistants like Claude to search the web for up-to-date information during conversations with users. This repository provides

## Overview

- **Category:** Search & Knowledge
- **Language:** Python
- **Stars:** 93
- **Forks:** 2
- **Owner:** ConechoAI
- **GitHub:** https://github.com/ConechoAI/openai-websearch-mcp
- **Created:** 2025-03-12T05:59:19+00:00
- **Updated:** 2025-03-26T15:47:22+00:00
- **Source:** https://model-context-protocol.com/servers/openai-websearch-mcp-server-ai-assistants

## Setup

## Setup

**One-click Installation & Configuration:**

*   **Claude:**
    ```bash
    OPENAI_API_KEY=sk-xxxx uv run --with uv --with openai-websearch-mcp openai-websearch-mcp-install
    ```

**Manual Installation and Configuration:**

1.  Make sure `uvx` is installed.
2.  **Claude:**
    *   **Using uvx:**
        ```json
        "mcpServers": {
          "openai-websearch-mcp": {
            "command": "uvx",
            "args": ["openai-websearch-mcp"],
            "env": {
                "OPENAI_API_KEY": "your-api-key-here"
            }
          }
        }
        ```
    *   **Using pip installation:**
        1.  Install `openai-websearch-mcp` via pip:
            ```bash
            pip install openai-websearch-mcp
            ```
        2.  Modify your Claude settings:
            ```json
            "mcpServers": {
              "openai-websearch-mcp": {
                "command": "python",
                "args": ["-m", "openai_websearch_mcp"],
                "env": {
                    "OPENAI_API_KEY": "your-api-key-here"
                }
              }
            }
            ```
3.  **Zed:**
    *   **Using uvx:**
        ```json
        "context_servers": [
          "openai-websearch-mcp": {
            "command": "uvx",
            "args": ["openai-websearch-mcp"],
            "env": {
                "OPENAI_API_KEY": "your-api-key-here"
            }
          }
        ],
        ```
    *   **Using pip installation:**
        ```json
        "context_servers": {
          "openai-websearch-mcp": {
            "command": "python",
            "args": ["-m", "openai_websearch_mcp"],
            "env": {
                "OPENAI_API_KEY": "your-api-key-here"
            }
          }
        },
        ```
4.  **Debugging:**
    *   For uvx installations:
        ```bash
        npx @modelcontextprotocol/inspector uvx openai-websearch-mcp
        ```

## Tools

## Available Tools

1.  `web_search` - Call openai websearch as tool.