Web Toolset#

Generated byAI

This toolset provides tools for interacting with web resources via HTTP requests.

`http_get_text_tool`#

Makes an HTTP GET request to a given URL that returns text content, and returns the content type and content.

Parameter	Type	Required	Description
`url`	String	Yes	The URL to GET text from.
`user_agent`	String	No	Optional user agent header; default is Firefox for macOS.
`preserve_html`	Boolean	No	Optional flag to preserve all the HTML content; default is false.
`accept`	String	No	Optionally specify an acceptable content type (e.g. `text/markdown`) to ask the server for specific format. Default is none.

Input:

{
  "url": "https://example.com",
  "user_agent": "MyCustomAgent/1.0",
  "preserve_html": false,
  "accept": "text/html"
}

Output:

{
  "content_type": "text/html",
  "body": "<html>...reduced HTML content...</html>"
}

Missing URL:

{
  "error": "The required URL was not specified"
}

Non-text Content:

{
  "error": "HTTP request did not return text content; it's content type was: image/png"
}

HTTP Request Failed:

{
  "error": "HTTP request failed with status: 404"
}

Content Too Large:

{
  "error": "Received content > 256000. Response is too big."
}

Network Error:

{
  "error": "An error occurred while making the HTTP request: Connection refused"
}

The tool strips line indents and coalesces line breaks for HTML, JSON, and XML content.
Unless preserve_html is set to true, it removes the head, script, and style elements as well as all class attributes from HTML content.
The maximum allowed content size is 256KB. Larger responses will result in an error.