A Model Context Protocol (MCP) server that bridges MCP-compatible clients with the Microsoft Bing Search API, exposing three tools for AI assistants: web, news, and image searches. It enables performing general web searches, retrieving recent news articles, and locating relevant images by issuing Bing requests with parameters such as query, count, market, and optional freshness. The server expects a Bing API key (BING_API_KEY) and can optionally use a custom API URL (BING_API_URL). It supports runtime configuration via environment variables and can be started with a command such as 'uvx bing-search-mcp'. The implementation includes rate limiting to prevent API abuse and comprehensive error handling to surface issues to clients. It is designed for Python 3.10+ and is installed via 'pip install -e .'. The MCP server is intended to work with MCP-compatible clients (e.g., Claude Desktop, Cursor) and can be configured in the clients’ MCP settings to point to the server command and environment variables. Available tools include bing_web_search, bing_news_search, and bing_image_search with their respective parameter sets.