Zephex_dev_info

Reads a public URL and returns the content in a model-friendly format without browser clutter.

DESCRIPTION

Use Zephex_dev_info when an agent needs documentation, an API reference, or a public web page in a compact format. It turns noisy web content into something a model can actually work with.

WHEN TO USE

GOOD FIT

Reading public documentation without opening a browser.
Pulling a clean API reference into an agent workflow.
Comparing several public pages without manual copy-paste.

AVOID IT WHEN

You need TLS, redirect, or security header analysis; use audit_headers.
You need local repo code analysis.
You need to inspect a private page the service cannot reach.

PARAMETERS

Name	Type	Required	Description
url	string	Yes	Public URL to inspect.

DETAILS

PUBLIC CONTENT ONLY

What this can and cannot reach

Zephex_dev_info works best on public documentation, changelogs, blog posts, and reference pages. If the page requires private network access, SSO, or credentials that the hosted service does not have, the request will fail like any other external fetch.

EXAMPLE

{  "jsonrpc": "2.0",  "id": 7,  "method": "tools/call",  "params": {    "name": "Zephex_dev_info",    "arguments": {      "url": "https://example.com/docs/auth"    }  }}

OUTPUT

Title: Authentication GuideSource: https://example.com/docs/authContent:# Authentication Send a Bearer token on every request. Rotate keys every 90 days and revoke immediately if exposed...

TOKEN EFFICIENCY

Clean extracted page content is usually around 600 to 1,500 tokens. Copying raw HTML or a full rendered page into context can easily cost 20,000 to 100,000 tokens and still be harder to read.