web_url_reader
ActiveTool of Inferventis — Financial Data, News & Web MCP
Fetches any public web page and returns clean, readable plain text stripped of HTML, navigation, scripts, advertisements, and boilerplate. Returns the page title, meta description, word count, and main body text ready for analysis or summarisation. Use this tool when an agent needs to read the content of a specific web page or article URL — for example to summarise an article, extract facts from a page, verify a claim by reading the source, or convert a web page into plain text to pass to another tool. Pass article URLs returned by web_news_headlines to this tool to read full article content. Do not use this tool to discover current news headlines — use web_news_headlines instead. Does not execute JavaScript — best suited for standard HTML content pages. Will not work with paywalled, login-protected, or JavaScript-rendered single-page applications.
Parameters schema
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The full public URL to fetch and read. Must include the scheme. Examples: 'https://en.wikipedia.org/wiki/Artificial_intelligence', 'https://www.bbc.com/news/technology-12345678'. Only HTTP and HTTPS URLs are supported."
},
"max_chars": {
"type": "number",
"description": "Maximum number of characters to return from the page body text. Defaults to 8000. Set higher (up to 50000) for long articles or documents. Set lower for quick headline extraction. The response indicates whether content was truncated."
},
"include_links": {
"type": "boolean",
"description": "Whether to include a list of hyperlinks found on the page alongside the text content. Defaults to false. Set to true when the agent needs to discover further URLs to follow, such as when crawling a site or finding references."
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
Inferventis — Financial Data, News & Web MCP
https://github.com/Bankee-ai/inferventis-tools
1/7 registries