PluginBench
MCP Server
Maintained
MIT

io.github.mcpware/pagecast MCP Server

io.github.mcpware/pagecast

Record browser interactions as polished GIF or MP4 demos with auto-zoom tooltips and cinematic effects.

What is the io.github.mcpware/pagecast MCP server?

Pagecast is an MCP server that records browser page interactions and exports them as production-ready GIF or MP4 files with automatic zoom overlays and cinematic pan effects. It injects cursor highlights and click ripples, then uses AI-driven interactions to create professional product demos without manual recording or video editing.

Pagecast automates the creation of product demo videos by recording browser interactions and applying professional visual effects like tooltip zoom overlays and cinematic camera pans. Instead of manually recording and editing videos, you tell your AI to demo your app—it records the interactions, and Pagecast automatically exports a polished GIF or MP4 optimized for your target platform (GitHub, YouTube, Instagram, TikTok, etc.).

How to install io.github.mcpware/pagecast

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "pagecast": {
      "command": "npx",
      "args": [
        "-y",
        "@mcpware/pagecast"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • record_page — Open a URL and start recording with auto-injected cursor highlight and click ripple effects.
  • interact_page — Perform interactions (scroll, click, hover, type, press keys, select, navigate, waitForSelector) that are captured with bounding boxes and timestamps.
  • stop_recording — Stop recording and save the WebM video file and timeline JSON with interaction event data.
  • smart_export — Export recording with tooltip overlay mode—magnified close-up insets appear near each interaction.
  • cinematic_export — Export recording with cinematic crop-pan mode—camera follows and zooms between interaction targets.
  • convert_to_gif — Convert WebM to optimized GIF with two-pass ffmpeg palette optimization, configurable FPS and width.
  • convert_to_mp4 — Convert WebM to H.264 MP4 ready for social media and embedding.
  • record_and_export — All-in-one tool: record a session and automatically export to GIF or MP4 based on platform preset.
  • list_recordings — List all WebM, GIF, and MP4 files in the output directory.

Use cases

  • Generate polished product demo GIFs for GitHub READMEs with automatic zoom on interactions.
  • Create vertical-format demo videos (1080×1920) for Instagram Reels, TikTok, and YouTube Shorts.
  • Record bug reports and QA captures with plain screen recording (no effects).
  • Rebuild demo videos automatically after UI changes without manual re-recording.
  • Export demos in platform-specific formats and sizes (YouTube 1280×720, Instagram 1080×1080, etc.) with one command.

io.github.mcpware/pagecast MCP server FAQ

What is Pagecast?

Pagecast is an MCP server that records browser interactions and exports them as professional GIF or MP4 demos with automatic zoom tooltips and cinematic pan effects. It's designed for AI agents to create product demos without manual recording or video editing.

Is Pagecast free?

Yes, Pagecast is open-source under the MIT license and available as an npm package.

How do I install Pagecast in Claude or Cursor?

Run `claude mcp add pagecast -- npx -y @mcpware/pagecast` or `cursor mcp add pagecast -- npx -y @mcpware/pagecast`. Requires Node.js ≥20 and ffmpeg. First-time setup: `npx playwright install chromium`.

What are the export modes?

Tooltip mode adds magnified close-ups near interactions (best for READMEs), cinematic mode pans the camera between actions (best for social media), and plain mode exports standard screen recordings without effects.

Can I customize video size and format?

Yes. Pagecast includes platform presets (GitHub, YouTube, Instagram, TikTok, etc.) that auto-set dimensions and format, or you can specify custom sizes and choose GIF or MP4 output.

Does Pagecast require authentication?

No, Pagecast does not require authentication. It runs locally using Playwright to control a Chromium browser.

README (reference)

Source of truth, from the repository.

Pagecast

npm version npm downloads license GitHub stars GitHub forks

English | 廣東話

Turn AI browser interactions into polished product demos.

Tell your AI to demo your app. Pagecast records the browser, tracks every click and keystroke, and exports a shipping-ready GIF or MP4 — with tooltip zoom overlays and cinematic pan effects. No screen recorder. No video editor. No post-production. Make a demo gif automatically after every PR if you want.

Without Pagecast — plain screen recording, you do the demonstration yourself and record yourself and you need to repead every time you changed the UI. You can see the cursor moving, but the actual interactions are too small to follow:

Original

With Pagecast (tooltip mode) — a magnified close-up appears on every interaction so viewers can actually see what's happening, and it design what to demo and make a new demo gif automatically:

Tooltip Demo

With Pagecast (cinematic mode) — the camera crops and pans to follow each action, and it design what to demo and make a new demo gif automatically:

Cinematic Demo

Two ways to use Pagecast

1. Product demo tool (the main use case)

You built a web app. You need a demo GIF for the README. Normally you'd:

  1. Open a screen recorder, manually click through the demo
  2. Open a video editor, zoom into the important parts
  3. Export, figure out ffmpeg, optimize the file size
  4. UI changes → repeat everything

With Pagecast, you tell your AI:

"Record a demo of localhost:3000 for my GitHub README"

The AI opens a real browser, interacts with your app, and exports a polished GIF with auto-zoom on every interaction. UI changes? Just re-run. The demo rebuilds itself.

2. Screen recording tool (also works)

Don't need zoom effects? Pagecast works as a plain screen recorder too:

"Record my app for 10 seconds and export as MP4"

The AI records, you get a .webm → optimized .gif or .mp4. Two-pass ffmpeg palette optimization, platform-aware sizing, one tool call.

Export Modes

ModeToolWhat it doesBest for
Tooltipsmart_exportFull viewport visible + magnified tooltip inset near each interactionREADME demos, product pages
Cinematiccinematic_exportCamera crops and pans to follow each interactionSocial media, dramatic reveals
Plainconvert_to_gif / convert_to_mp4Standard screen recording, no zoom effectsBug reports, QA captures

Just Say Where It's Going

You don't need to know viewport sizes or formats. Just tell your AI the destination:

"Record a demo for GitHub README"           → 1280×720 GIF
"Record my app for Instagram Reels"         → 1080×1920 MP4
"Make a TikTok demo of my dashboard"        → 1080×1920 MP4
"Record for YouTube"                        → 1280×720 MP4
PlatformSizeFormatAspect
github / readme1280×720GIF16:9
youtube / twitter1280×720MP416:9
reels / tiktok / shorts1080×1920MP49:16
instagram / linkedin1080×1080MP41:1
CustomAny sizeYour choiceAny

Quick Start

Node.js ≥ 20 and ffmpeg required.

# Add to Claude Code
claude mcp add pagecast -- npx -y @mcpware/pagecast

# Or run directly
npx @mcpware/pagecast

# Headless mode (no visible browser)
claude mcp add pagecast -- npx -y @mcpware/pagecast --headless

# First time: install browser
npx playwright install chromium

How It Works

You: "Record a demo of my app"
            ↓
AI → record_page(url, platform: "github")
    Opens Chromium (visible) at 1280×720
    Injects cursor highlight + click ripple
            ↓
AI → interact_page(click, type, hover...)
    Each action records bounding box + timestamp
            ↓
AI → stop_recording
    Saves .webm + timeline.json
            ↓
AI → smart_export (tooltip mode)
        or cinematic_export (crop-pan mode)
        or convert_to_gif (plain mode)
            ↓
    Shipping-ready .gif or .mp4

What makes the demo look professional:

  • Cursor highlight — red dot tracks the mouse so viewers can follow the action
  • Click ripple — visual feedback on every click
  • Tooltip overlay — magnified close-up appears near each interaction, with a small arrow pointing toward it
  • Cinematic pan — smooth crop transitions between interaction targets with easeInOut curves

MCP Tools

ToolWhat it does
record_pageOpen a URL, start recording. Auto-injects cursor highlight + click ripple
interact_pagescroll, click, hover, type, press keys, select, navigate, waitForSelector — all captured with bounding boxes
stop_recordingStop and save .webm + -timeline.json (event timeline with interaction positions)
smart_exportTooltip overlay — magnified tooltip close-up on each interaction
cinematic_exportCinematic crop-pan — camera follows the action between interaction targets
convert_to_gifWebM → optimized GIF (ffmpeg two-pass palette, configurable FPS/width/trim)
convert_to_mp4WebM → MP4 (H.264, ready for social/sharing/embedding)
record_and_exportAll-in-one: record → auto-export to GIF or MP4 based on platform
list_recordingsList all .webm, .gif, and .mp4 files in output directory

Comparison

AutomatedInteractionsDemo zoomOutputAI-drivenPlatform presets
Pagecast✅✅ click/type/scroll/hover✅ tooltip + cinematicGIF + WebM + MP4✅✅
Screen Studio❌ manual❌✅ cursor-basedMP4❌❌
AutoZoom❌ manual❌✅ click-basedMP4❌❌
Playwright MCP✅✅❌Raw .webmPartial❌
gifcap.dev / Peek / Kap❌ manual❌❌GIF❌❌
VHS (Charmbracelet)✅ scriptedTerminal only❌GIF❌❌

Screen Studio and AutoZoom have great zoom — but require manual recording. Pagecast is the only tool where the AI records AND the demo effects are automatic.

Configuration

SettingDefaultNotes
BrowserHeaded (visible)--headless for background
GIF FPS12Higher = smoother, larger
GIF width800pxHeight auto-scaled
Tooltip magnify1.6xHow much the tooltip zooms in
Tooltip size380pxSize of the tooltip inset
Cinematic zoom2.5xHow much the camera zooms in
Zoom transition0.35sSmoothstep ease-in/out duration
Cursor overlayOnRed dot + click ripple effect
Video viewport1280×720Or use platform parameter
Output dir./recordingsOverride: RECORDING_OUTPUT_DIR

Architecture

src/
├── index.js        # MCP server — 9 tools, platform presets, stdio transport
├── recorder.js     # Playwright browser lifecycle + sessions + event timeline
├── converter.js    # ffmpeg GIF/MP4 + tooltip overlay + cinematic zoom conversion
├── zoom.js         # Zoom engine — chains, panning, tooltip events, FFmpeg expressions
├── tooltip.js      # Tooltip PNG generator (rounded rect + arrow, pure Node.js)
└── remotion/
    ├── ZoomComposition.jsx  # React composition for cinematic zoom
    ├── Root.jsx             # Remotion entry point
    └── render.js            # Remotion CLI wrapper
  • Event timeline — every interaction records bounding box + timestamp
  • Cursor overlay — red dot + click ripple injected into the page
  • Tooltip overlay — magnified close-up in a clean tooltip frame with directional arrow
  • Cinematic zoom chains — nearby interactions form chains that zoom in, pan, zoom out
  • Thread-safe FFmpeg expressions — crop filters work correctly with multi-threaded encoding
  • Headed by default — watch what the AI does
  • execFile not exec — safe against shell injection

More from @mcpware

ProjectWhat it doesInstall
Instagram MCP23 Instagram Graph API tools — posts, comments, DMs, stories, analyticsnpx @mcpware/instagram-mcp
Claude Code OrganizerVisual dashboard for Claude Code memories, skills, MCP servers, hooksnpx @mcpware/claude-code-organizer
UI AnnotatorHover labels on any web page — AI references elements by namenpx @mcpware/ui-annotator
LogoLoomAI logo design → SVG → full brand kit exportnpx @mcpware/logoloom

License

MIT

Related MCP servers

Hover-labeled UI elements in any browser—no extensions, no code changes. AI-friendly element naming for seamless design collaboration.

16
JavaScript
MIT
View repository →

Organize Claude Code and Codex CLI config, memories, skills, MCP servers, and agents in one cross-harness dashboard.

369
JavaScript
MIT
View repository →

23 tools for Instagram Graph API: manage posts, DMs, stories, reels, and analytics from AI agents.

29
Python
MIT
View repository →

AI logo design to complete brand kit—SVG, PNG, ICO, WebP, social media sizes, all locally.

30
JavaScript
MIT
View repository →

U.S. Census (ACS) data by ZIP: income, demographics, housing, education, from a local store.

0
Python
MIT
View repository →

SEC filings in your agent: issuers, Reg CF/D/A raises, XBRL financials, insider trades.

1
Python
MIT
View repository →