create_og_image
Create Open Graph / social preview images.
How to use it
create_og_image is exposed by the Pagebolt MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the create_og_image tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL PAGEBOLT MCP LISTINGOther tools in Pagebolt MCP (39)
Goal-driven automation. Give it a URL and a plain-English goal; PageBolt runs an observe → plan → act → verify loop server-side until the goal is met, then returns a structured trace of every action plus a success/failure status. You do not author selectors or a step list — this is the "hands" on to
hosts the agent may navigate to (defaults to the start host only)
block advertisements
hide cookie consent banners
remove live chat widgets
block tracking scripts
style (ripple/pulse/ring), color
, headers, authorization — authenticated captures
{ username, password }, substituted at execution time only, never logged or sent to the planner LLM; shown in the trace as <redacted>
style (highlight/circle/spotlight/dot/classic), color, size, smoothing, persist
emulate dark color scheme
wait before capture (for animations)
get page title, description, OG tags alongside the screenshot
png, jpeg, or webp
24, 30, or 60 fps (default: 30)
capture the entire scrollable page
Generate a PDF from any URL or HTML content.
, timeZone — location emulation
plain-English outcome you want, e.g. "Log in and open the billing page" (required)
Convert a page-agent / browser-use action trace into a re-runnable PageBolt sequence. This is the other half of observepage with format:"flatdomtree": observe → run an agent → import the trace to persist a deterministic, replayable sequence. Does not consume request quota.
Inspect a web page and get a structured map of all interactive elements, headings, forms, links, and images — each with a unique CSS selector.
cap on planning iterations (default 8; clamped to your plan ceiling)
optional name for the sequence.
Get a compact, token-budgeted observation of any page, purpose-built for AI agents: id-indexed interactive elements (role, name, CSS selector, state), a heuristic page-type classification, and grouped suggested actions — optionally bundled with readable content, the ARIA tree, a screenshot, and cons
speed preset: "fast", "normal", "slow", "dramatic", "cinematic", or a number 0.25–6.0
Record a professional demo video of a multi-step browser automation sequence with cursor effects, click animations, smooth movement, and optional AI voice narration.
Execute multi-step browser automation.
true (default) persists the sequence; false is a dry run that returns the translated steps + stepcount without saving.
capture a specific DOM element
optional index→CSS map (e.g. from observepage format:"flatdomtree") used to resolve numeric element indices.
run inside an existing session to reuse cookies/login
same actions as runsequence (except no screenshot/pdf — the whole sequence is the video)
Capture a pixel-perfect screenshot of any URL, HTML, or Markdown.
array of action entries (required). Supports both {action, indexselector, value, ...} and {actionname: {...}} shapes.
"sequence" (default) or "video".
/ html / markdown — content source
device preset (e.g. "iphone14pro", "macbookpro14")
, height — viewport size (default: 1280x720)
auto-zoom on clicks with configurable level and duration