What it does
The tool takes one public web page and returns its content as clean markdown. Each result includes the page title, the detected language and a SHA-256 hash of the content.
It suits workflows where an assistant needs the readable text of a single web page in a consistent format, with the hash available to check the content later. It obeys robots.txt rules when fetching.
Limitations and requirements
Works on one public web page per request. Fetching respects the site's robots.txt rules, so pages those rules disallow are not retrieved.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
read_url
One public web page as clean markdown, with title, language and a SHA-256. Obeys robots.txt.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it