The MCP server io.github.mcpware/pagecast records a browser page as GIF or video via MCP. The project is associated with topics including browser automation, Playwright, screen capture, screencasting, and ffmpeg, and is implemented as an open-source TypeScript tool.
๐ ๏ธ Key Features
Records browser pages as GIF or video
Uses MCP as the integration interface
Related tooling/topics include playwright and ffmpeg
๐ Use Cases
Generate screencasts or screen recordings of browser activity
Capture demos for developer workflows or documentation
Automate browser capture using browser-automation
โก Developer Benefits
Fits Model Context Protocol (MCP)-based automation pipelines
Supports developer tooling categories such as developer-tools, ai-tools, and demo
โ ๏ธ Limitations
The available description only specifies GIF/video recording via MCP; other capabilities are not described here.
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 โ 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 โ 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:
With Pagecast (tooltip mode) โ 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) โ 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:
Open a screen recorder, manually click through the demo
Open a video editor, zoom into the important parts
Export, figure out ffmpeg, optimize the file size
UI changes โ repeat everything
With Pagecast, you tell your AI:
code
"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:
code
"Record my app for 10 seconds and export as MP4"
The AI records, you get a .webm โ optimized .gif or .mp4. Two-pass ffmpeg palette optimization, platform-aware sizing, one tool call.
Export Modes
Mode
Tool
What it does
Best for
Tooltip
smart_export
Full viewport visible + magnified tooltip inset near each interaction
README demos, product pages
Cinematic
cinematic_export
Camera crops and pans to follow each interaction
Social media, dramatic reveals
Plain
convert_to_gif / convert_to_mp4
Standard screen recording, no zoom effects
Bug 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:
code
"Record a demo for GitHub README" โ 1280ร720 GIF
"Record my app for Instagram Reels" โ 1080ร1920 MP4
"Make a TikTok demo of my dashboard" โ 1080ร1920 MP4
"Record for YouTube" โ 1280ร720 MP4
Platform
Size
Format
Aspect
github / readme
1280ร720
GIF
16:9
youtube / twitter
1280ร720
MP4
16:9
reels / tiktok / shorts
1080ร1920
MP4
9:16
instagram / linkedin
1080ร1080
MP4
1:1
Custom
Any size
Your choice
Any
Quick Start
Node.js โฅ 20 and ffmpeg required.
bash
# 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
code
You: "Record a demo of my app"
โ
AI โ record_page(url, platform: "github")
Opens Chromium (visible) at 1280ร720
Injects cursor highlight + click ripple
โ
AI โ interact_page(click, type, hover...)
Each action records bounding box + timestamp
โ
AI โ stop_recording
Saves .webm + timeline.json
โ
AI โ smart_export (tooltip mode)
or cinematic_export (crop-pan mode)
or convert_to_gif (plain mode)
โ
Shipping-ready .gif or .mp4
What makes the demo look professional:
Cursor highlight โ red dot tracks the mouse so viewers can follow the action
Click ripple โ visual feedback on every click
Tooltip overlay โ magnified close-up appears near each interaction, with a small arrow pointing toward it
Cinematic pan โ smooth crop transitions between interaction targets with easeInOut curves
MCP Tools
Tool
What it does
record_page
Open a URL, start recording. Auto-injects cursor highlight + click ripple
interact_page
scroll, click, hover, type, press keys, select, navigate, waitForSelector โ all captured with bounding boxes
stop_recording
Stop and save .webm + -timeline.json (event timeline with interaction positions)
smart_export
Tooltip overlay โ magnified tooltip close-up on each interaction
cinematic_export
Cinematic crop-pan โ camera follows the action between interaction targets
WebM โ MP4 (H.264, ready for social/sharing/embedding)
record_and_export
All-in-one: record โ auto-export to GIF or MP4 based on platform
list_recordings
List all .webm, .gif, and .mp4 files in output directory
Comparison
Automated
Interactions
Demo zoom
Output
AI-driven
Platform presets
Pagecast
โ
โ click/type/scroll/hover
โ tooltip + cinematic
GIF + WebM + MP4
โ
โ
Screen Studio
โ manual
โ
โ cursor-based
MP4
โ
โ
AutoZoom
โ manual
โ
โ click-based
MP4
โ
โ
Playwright MCP
โ
โ
โ
Raw .webm
Partial
โ
gifcap.dev / Peek / Kap
โ manual
โ
โ
GIF
โ
โ
VHS (Charmbracelet)
โ scripted
Terminal only
โ
GIF
โ
โ
Screen Studio and AutoZoom have great zoom โ but require manual recording. Pagecast is the only tool where the AI records AND the demo effects are automatic.