An SSE-based MCP server example designed to let an AI Agent search for external information through SearXNG's open-source meta-search engine and retrieve results as Markdown. The server runs with uv to manage dependencies and the Python runtime, and connects to a SearXNG instance via a configurable SEARXNG_URL. It integrates Microsoft's markdownify to extract web pages into Markdown-formatted text for downstream processing. The project includes a pre-configured SearXNG setup under searxng-docker to facilitate testing, with a docker-compose.yaml and searxng settings. The MCP server exposes tools via MCP Inspector (web_search and web_url_read) and can be run as an SSE service on port 5488 by default. Startup parameters include host, port, and searxng_url, enabling flexible deployment. The README provides instructions for starting the SearXNG service, starting the MCP server via uv run server.py, or via Docker, and for verifying results using the MCP Inspector app. This makes it suitable for cloud-native, decoupled AI workflows.