What it does
An active MCP reference server (Python) that fetches a URL and converts HTML to markdown so an LLM can read content without raw markup. Supports chunked reading for long pages and options for user-agent and proxy. Fetch + conversion is deterministic. Runs locally over stdio. (Note: it can reach internal addresses — a documented SSRF caution for self-hosters.)
Example prompts
- Fetch this article URL and give me a clean markdown version.
- Read the docs page at this link and summarize the key steps.
