"author:mrlong0129" matching MCP servers:

Exposes two tools, fetch_page and extract_from_html, so agents can retrieve web pages as markdown or plain text without ever launching a separate install step. Fetching escalates cheapest-first (HTTP requests, identity switching, JSON-LD/JS-state/AMP/feed extraction, then optional headless browser) and always returns a machine-readable reason such as captcha, login wall, or paywall when a page cannot be read.

Enables agents to retrieve public WeChat Official Account articles as clean Markdown or JSON and parse saved WeChat HTML through MCP tools.