capture_screenshot
Capture webpage screenshots as base64-encoded PNG images. Use this tool to visually document web content, wait for page loading, and optionally save screenshots to local directories for web analysis and documentation.
Instructions
[STATELESS] Capture webpage screenshot. Returns base64-encoded PNG data. Creates new browser each time. Optionally saves screenshot to local directory. IMPORTANT: Chained calls (execute_js then capture_screenshot) will NOT work - the screenshot won't see JS changes! For JS changes + screenshot use create_session + crawl(session_id, js_code, screenshot:true) in ONE call.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| save_to_directory | No | Directory path to save screenshot (e.g., ~/Desktop, /tmp). Do NOT include filename - it will be auto-generated. Large screenshots (>800KB) won't be returned inline when saved. | |
| screenshot_wait_for | No | Seconds to wait before taking screenshot (allows page loading/animations) | |
| url | Yes | The URL to capture |
Input Schema (JSON Schema)
{
"properties": {
"save_to_directory": {
"description": "Directory path to save screenshot (e.g., ~/Desktop, /tmp). Do NOT include filename - it will be auto-generated. Large screenshots (>800KB) won't be returned inline when saved.",
"type": "string"
},
"screenshot_wait_for": {
"default": 2,
"description": "Seconds to wait before taking screenshot (allows page loading/animations)",
"type": "number"
},
"url": {
"description": "The URL to capture",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
}