drio
Open app

OpenAI WebSearch MCP Server

Source

openai websearch tool as mcp server

Catalog onlyCatalog onlySTDIO

Overview

OpenAI WebSearch MCP Server is a tool that provides access to OpenAI's web search functionality through the Model Context Protocol, enabling AI assistants to search the web for real-time information during user interactions.

To use the server, you can install it via pip or use the recommended uv method. After installation, configure it for use with applications like Claude.app or Zed editor by setting the appropriate commands and environment variables.

  • Access to real-time web search capabilities for AI assistants. - Configurable for different environments (Claude.app, Zed editor). - Supports user location context for personalized search results.
  1. Enhancing AI assistants with up-to-date information during conversations.
  2. Providing context-aware search results based on user location.
  3. Integrating web search functionality into various applications.

Add to your AI client

Use these steps to connect OpenAI WebSearch MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "openai-websearch-mcp-conechoai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-openai-websearch-mcp-conechoai"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "openai-websearch-mcp-conechoai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-openai-websearch-mcp-conechoai"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "openai-websearch-mcp-conechoai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-openai-websearch-mcp-conechoai"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "openai-websearch-mcp-conechoai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-openai-websearch-mcp-conechoai"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "openai-websearch-mcp-conechoai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-openai-websearch-mcp-conechoai"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "openai-websearch-mcp-conechoai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-openai-websearch-mcp-conechoai"
      ]
    }
  }
}

FAQ

**What programming language is used?**

The server is implemented in Python.

**Is there a license for this project?**

Yes, it is licensed under the MIT license.

**How can I debug the server?**

You can use the MCP inspector for debugging, especially for `uvx` installations.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":2379,"uuid":"d8298b95-7e26-4660-94b7-141a4bce8995","name":"openai-websearch-mcp","title":"OpenAI WebSearch MCP Server","description":"openai websearch tool as mcp server","avatar_url":"https://avatars.githubusercontent.com/u/199111139?v=4","created_at":"2025-03-13T07:05:34.604Z","updated_at":"2025-03-13T08:17:57.497Z","status":"created","author_name":"ConechoAI","author_avatar_url":"https://avatars.githubusercontent.com/u/199111139?v=4","tags":"[]","category":"developer-tools","is_featured":false,"sort":1,"url":"https://github.com/ConechoAI/openai-websearch-mcp/","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"40\",\"license\":\"MIT license\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-03-13 23:18:47\"}","user_uuid":"75f2daed-3a30-49b4-b710-394315e3618a","tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Developer tools
OpenAI WebSearch MCP Server — MCP Registry