{"serverId":"mcp-registry/com.mcpscores/web-extract","tools":[{"name":"read_page","fixed":{"name":"read_page","description":"Fetch a URL and return its readable text with scripts, styles, navigation and markup stripped, plus the title, description, site name and publication date from the page's own metadata. Use whenever you need the contents of a page rather than a search result about it. Output is capped so it fits a prompt — raise maxChars if you need more. JavaScript is not executed, so a page that renders entirely client-side returns its shell, and the character count tells you when that happened. A site that blo","inputSchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","examples":["https://en.wikipedia.org/wiki/Web_scraping"],"description":"Absolute http(s) URL of the page to read."},"maxChars":{"type":"string","examples":["12000"],"description":"Maximum characters of text to return. Default 12000, maximum 60000."}},"additionalProperties":false},"annotations":{"readOnlyHint":true},"title":"Read a web page as clean text"},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":252,"tokensAfter":252}],"toolsChanged":1,"tokensSaved":0,"todo":[],"note":"Deterministic fixes. Changes marked verify need a human look before shipping (renames, inferred annotations, inferred types, removed text). Parameter descriptions in `todo` need to be written by someone who knows the API."}