Capture a webpage screenshot from the terminal, as an approved step
Point Luumen at a URL and get a screenshot back. Useful when you need visual proof that a status page, dashboard, or customer-facing site renders the way you think it does during an incident or after a change. Capture runs through SCREENSHOT_FYI_TAKE_SCREENSHOT, which asks for your approval before it fires by default. Connect with an API key.
1 tools: 0 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — take screenshot — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Screenshot.fyi — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.