The OpenAI WebSearch MCP Server provides AI assistants with access to real-time web search capabilities through OpenAI's websearch functionality. Developed by ConechoAI, this Python-based implementation allows Claude and other AI assistants to search the web during conversations, retrieving up-to-date information not available in their training data. The server supports configurable search context sizes and user location parameters, making it particularly valuable for answering questions about current events, retrieving recent information, or accessing specialized knowledge that may be outside an assistant's knowledge cutoff. It can be easily installed via pip or uv and configured for use with Claude.app or Zed editor.
Call OpenAI websearch as a tool. Required arguments: type (string): web_search_preview, search_context_size (string): High level guidance for the amount of context window space to use for the search (low, medium, or high; medium is the default), user_location (object or null) which includes type (string): approximation, city (string), country (string): two-letter ISO country code, region (string), timezone (string): IANA timezone.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIOur bundler currently only supports TypeScript-based servers. Check back soon!