Pagebolt MCP
未申請An MCP server to allow AI agents to interact with PageBolt to take screenshots, grab PDFs, and more.
未申請リスティング
このMCPサーバーはあなたのものですか？
このリスティングは公開情報から自動的にインデックスされました。申請することで、ページの編集、互換性の設定、成長ツールのアンロックができます。2分以内に完了します。
このサーバーを申請するツール（40個）
act_on_page
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
allowedDomains
hosts the agent may navigate to (defaults to the start host only)
blockAds
block advertisements
blockBanners
hide cookie consent banners
blockChats
remove live chat widgets
blockTrackers
block tracking scripts
clickEffect
style (ripple/pulse/ring), color
cookies
, headers, authorization — authenticated captures
create_og_image
Create Open Graph / social preview images.
credentials
{ username, password }, substituted at execution time only, never logged or sent to the planner LLM; shown in the trace as <redacted>
cursor
style (highlight/circle/spotlight/dot/classic), color, size, smoothing, persist
darkMode
emulate dark color scheme
delay
wait before capture (for animations)
extractMetadata
get page title, description, OG tags alongside the screenshot
format
png, jpeg, or webp
framerate
24, 30, or 60 fps (default: 30)
fullPage
capture the entire scrollable page
generate_pdf
Generate a PDF from any URL or HTML content.
geolocation
, timeZone — location emulation
goal
plain-English outcome you want, e.g. "Log in and open the billing page" (required)
import_agent_trace
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_page
Inspect a web page and get a structured map of all interactive elements, headings, forms, links, and images — each with a unique CSS selector.
maxSteps
cap on planning iterations (default 8; clamped to your plan ceiling)
name
optional name for the sequence.
observe_page
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
pace
speed preset: "fast", "normal", "slow", "dramatic", "cinematic", or a number 0.25–6.0
record_video
Record a professional demo video of a multi-step browser automation sequence with cursor effects, click animations, smooth movement, and optional AI voice narration.
run_sequence
Execute multi-step browser automation.
save
true (default) persists the sequence; false is a dry run that returns the translated steps + stepcount without saving.
selector
capture a specific DOM element
selectors
optional index→CSS map (e.g. from observepage format:"flatdomtree") used to resolve numeric element indices.
session_id
run inside an existing session to reuse cookies/login
steps
same actions as runsequence (except no screenshot/pdf — the whole sequence is the video)
take_screenshot
Capture a pixel-perfect screenshot of any URL, HTML, or Markdown.
trace
array of action entries (required). Supports both {action, indexselector, value, ...} and {actionname: {...}} shapes.
type
"sequence" (default) or "video".
url
/ html / markdown — content source
viewportDevice
device preset (e.g. "iphone14pro", "macbookpro14")
width
, height — viewport size (default: 1280x720)
zoom
auto-zoom on clicks with configurable level and duration