Read a web page as Markdown
read_webpageFetch a public web page and return its main content as Markdown, stripping ads, navigation, and scripts. For JavaScript pages, set render to true.
Instructions
Fetches a public web page and returns its main content as Markdown, without navigation, adverts or scripts. For pages that build their content with JavaScript, set render to true.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "read_webpage"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The page to read. | |
| mode | No | `article` (default) keeps the main content. `full` converts the whole body. | article |
| fresh | No | When true, bypasses the cache. | |
| links | No | When false, replaces links with their text. | |
| images | No | When false, drops images from the output. | |
| render | No | When true, loads the page in a headless browser first. | |
| max_chars | No | Longest Markdown to return, in characters, from 1000 to 500000. Sent as 20000 when omitted. The reply says whether the text was cut short. |