page_snapshot

MCP tool from Drissionpage MCP Server by jumodada

Return a bounded page outline with headings, links, buttons, inputs, forms, and selector recommendations

How to use it

page_snapshot is exposed by the Drissionpage MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the page_snapshot tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

FULL DRISSIONPAGE MCP SERVER LISTING

Other tools in Drissionpage MCP Server (39)

element_check

Check or uncheck checkbox/radio controls

element_click

Click any element with additive left/right/middle and single/double-click semantics

element_click_and_download

Correlate one selector, coordinate, or keyboard trigger with one integrity-checked artifact under DPMCPDOWNLOADROOT

element_click_and_upload

Arm Chromium's file chooser, click its trigger, inject approved files, and clean interception without an operating-system picker

element_find

Find one element by CSS selector or XPath; bare selectors like h1 are treated as CSS

element_find_all

Extract bounded repeated elements with text, attributes, and recommended selectors

element_get_attribute

Get an HTML attribute

element_get_html

Get element or page HTML

element_get_property

Get a live DOM property such as an input value

element_get_text

Get element or page text

element_hover

Hover an element to trigger menu/tooltip states

element_scroll_into_view

Bring an element into the viewport before acting

element_select

Select an option by value, text, or index

element_state_get

Read live DrissionPage state flags and document/viewport geometry for one element

element_type

Input text into elements

element_upload_file

Use elementuploadfile(paths=[...]) to upload files from DPMCPUPLOADROOT to input[type=file]

keyboard_press

Send keys to the active element/page without echoing the input in results

page_accessibility_snapshot

Return a bounded Chromium accessibility tree for the page or a scoped element, with field values redacted unless explicitly requested

page_click_xy

Move with direct or natural motion, optionally wait for an explicit delay, then press and release at the exact target

page_close

Close browser

page_evaluate

Run bounded JavaScript in the current page and return a JSON-safe result

page_export_artifact

Generate a managed PDF or MHTML artifact under DPMCPARTIFACTROOT with SHA-256 and receipt evidence

page_get_url

Get current URL

page_go_back

Navigate backward in browser history

page_go_forward

Navigate forward in browser history

page_navigate

Navigate to any URL; optionally open it in a new tab with newtab or return an observe change summary

page_navigate_with_http_auth

Navigate through a scoped HTTP auth challenge in a dedicated disposable Chromium context without returning credentials

page_observe

Return a compact page fingerprint with URL, title, counts, visible text samples, active element, and recent console summary

page_pointer_drag

Perform one failure-safe coordinate drag through up to six optional ordered waypoints with the selected profile

page_pointer_drag_element

Resolve source and destination geometry immediately before dragging; supports CSS/XPath in the top document or one same-origin iframe, plus CSS paths through nested open Shadow DOM hosts

page_pointer_move

Move to exact viewport CSS coordinates with direct or bounded deterministic natural motion

page_refresh

Reload current page

page_resize

Adjust browser window

page_screenshot

Capture an inline full-page or viewport screenshot

page_screenshot_save

Save a screenshot under DPMCPSCREENSHOTROOT

page_scroll

Use pagescroll(pixels=...) for relative scrolling, or pass x/y for an absolute position

tab_close

Close one tab without closing the whole browser

tab_list

List open browser tabs with stable MCP tab IDs

tab_switch

Switch to a tab returned by tablist