pagecast
Pagecast
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:

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:

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:

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 → 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.
Related MCP server: autodemo
Export Modes
Mode | Tool | What it does | Best for |
Tooltip |
| Full viewport visible + magnified tooltip inset near each interaction | README demos, product pages |
Cinematic |
| Camera crops and pans to follow each interaction | Social media, dramatic reveals |
Plain |
| 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:
"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 MP4Platform | Size | Format | Aspect |
| 1280×720 | GIF | 16:9 |
| 1280×720 | MP4 | 16:9 |
| 1080×1920 | MP4 | 9:16 |
| 1080×1080 | MP4 | 1:1 |
Custom | Any size | Your choice | Any |
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 chromiumHow 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 .mp4What 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
Tool | What it does |
| Open a URL, start recording. Auto-injects cursor highlight + click ripple |
| scroll, click, hover, type, press keys, select, navigate, waitForSelector — all captured with bounding boxes |
| Stop and save |
| Tooltip overlay — magnified tooltip close-up on each interaction |
| Cinematic crop-pan — camera follows the action between interaction targets |
| WebM → optimized GIF (ffmpeg two-pass palette, configurable FPS/width/trim) |
| WebM → MP4 (H.264, ready for social/sharing/embedding) |
| All-in-one: record → auto-export to GIF or MP4 based on platform |
| List all |
Comparison
Automated | Interactions | Demo zoom | Output | AI-driven | Platform presets | |
Pagecast | ✅ | ✅ click/type/scroll/hover | ✅ tooltip + cinematic | GIF + WebM + MP4 | ✅ | ✅ |
Screen Studio | ❌ manual | ❌ | ✅ cursor-based | MP4 | ❌ | ❌ |
AutoZoom | ❌ manual | ❌ | ✅ click-based | MP4 | ❌ | ❌ |
Playwright MCP | ✅ | ✅ | ❌ | Raw | Partial | ❌ |
gifcap.dev / Peek / Kap | ❌ manual | ❌ | ❌ | GIF | ❌ | ❌ |
VHS (Charmbracelet) | ✅ scripted | Terminal 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
Setting | Default | Notes |
Browser | Headed (visible) |
|
GIF FPS | 12 | Higher = smoother, larger |
GIF width | 800px | Height auto-scaled |
Tooltip magnify | 1.6x | How much the tooltip zooms in |
Tooltip size | 380px | Size of the tooltip inset |
Cinematic zoom | 2.5x | How much the camera zooms in |
Zoom transition | 0.35s | Smoothstep ease-in/out duration |
Cursor overlay | On | Red dot + click ripple effect |
Video viewport | 1280×720 | Or use |
Output dir |
| Override: |
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 wrapperEvent 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
execFilenotexec— safe against shell injection
More from @mcpware
Project | What it does | Install |
23 Instagram Graph API tools — posts, comments, DMs, stories, analytics |
| |
Visual dashboard for Claude Code memories, skills, MCP servers, hooks |
| |
Hover labels on any web page — AI references elements by name |
| |
AI logo design → SVG → full brand kit export |
|
License
MIT
Available Tools
9 toolscinematic_exportA
Convert a recorded .webm to GIF or MP4 with cinematic crop-pan effects.
Crops the entire frame to focus on the interaction area, then pans smoothly between targets. Think of it as a virtual cameraman that follows the action.
Two rendering modes:
"quick" (default): FFmpeg-based crop with smoothstep easing. Fast, no extra dependencies.
"cinematic": Remotion-based rendering with spring animations. Requires remotion + react installed.
Example workflow:
record_page → interact_page (clicks, typing, etc.) → stop_recording
cinematic_export with the webmPath and timelinePath from stop_recording
Get a polished GIF/MP4 where the camera follows the action
Inputs: webmPath (required), timelinePath (required), fps, mode, +5 more.
convert_to_gifB
Convert a .webm video to an optimized GIF using ffmpeg two-pass palette method.
Inputs: webmPath (required), fps, width, startTime.
convert_to_mp4A
Convert a .webm video to MP4 (H.264). Widely compatible for social media, sharing, and embedding.
Inputs: webmPath (required), crf.
interact_pageA
Perform actions on a recording page (scroll, click, hover, type, press, select, wait, navigate). Actions are performed sequentially and recorded in the video.
Inputs: actions (required), sessionId (required).
list_recordingsA
List all .webm and .gif recordings in the output directory.
Inputs: directory.
record_and_exportA
All-in-one: open URL, wait for specified duration, stop recording, auto-export to the right format.
Use the "platform" parameter and we handle everything:
"Record a demo for my GitHub README" → platform: "github" → 1280×720 GIF
"Record my app for Instagram Reels" → platform: "reels" → 1080×1920 MP4
"Make a TikTok demo" → platform: "tiktok" → 1080×1920 MP4
"Record for YouTube" → platform: "youtube" → 1280×720 MP4
Or pass custom width/height/outputFormat for full control.
Inputs: url (required), width, gifFps, height, +4 more.
record_pageA
Open a URL in a browser and start recording video. Returns a session ID. Call stop_recording when done.
Instead of specifying width/height, you can use the "platform" parameter:
"Record my app for GitHub README" → platform: "github" (1280×720, GIF)
"Record my app for Instagram Reels" → platform: "reels" (1080×1920, MP4)
"Record my app for TikTok" → platform: "tiktok" (1080×1920, MP4)
"Record my app for YouTube" → platform: "youtube" (1280×720, MP4)
"Record my app for YouTube Shorts" → platform: "shorts" (1080×1920, MP4)
"Record my app for Instagram post" → platform: "instagram" (1080×1080, MP4)
"Record my app for LinkedIn" → platform: "linkedin" (1080×1080, MP4)
"Record my app for Twitter" → platform: "twitter" (1280×720, MP4)
Or pass custom width/height for any other size.
Inputs: url (required), width, height, platform.
smart_exportA
Convert a recorded .webm to GIF or MP4 with tooltip overlays on interactions.
The full viewport stays visible. When an interaction happens (click, type, hover), a clean tooltip inset appears showing a magnified close-up of that area with a small arrow pointing toward the interaction. Modern, minimal design (Linear/Figma style).
The tooltip positions itself on the opposite side of the screen from the interaction.
Perfect for product demos where viewers need to see both the full UI context AND the detail.
Example workflow:
record_page → interact_page (clicks, typing, etc.) → stop_recording
smart_export with the webmPath and timelinePath from stop_recording
Get a polished GIF/MP4 with tooltip overlays on every interaction
Compare with cinematic_export which crops the entire frame to follow the action.
Inputs: webmPath (required), timelinePath (required), fps, width, +4 more.
stop_recordingA
Stop a recording session and save the video as .webm file.
Inputs: sessionId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: recording, interacting, stopping, converting, listing, and combining steps. Even the two export tools (cinematic_export vs smart_export) are well-differentiated in their descriptions.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., record_page, interact_page, stop_recording, convert_to_gif, list_recordings). No mixing of conventions.
With 9 tools, the server is well-scoped for its purpose of recording, interacting, exporting, and managing recordings. This is within the ideal range and each tool serves a clear function.
The tool surface covers the full recording-to-export workflow, including a combined tool. Minor gaps: no delete or file management tool, and no pause/resume for recording, but these are non-critical.
Maintenance
Related MCP Connectors
- RecordHTMLDeprecatedcom.recordhtml
Record web pages and HTML5 creatives to MP4, WebM or GIF in a real browser.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.
Unofficial Browserless MCP — wraps the Browserless headless-Chromium REST API (browserless.io)
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server for screen recording on macOS, iOS Simulator, and Android, with key-frame extraction via ffmpeg, enabling AI agents to capture UI motion and transient visual states.121MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that turns any running web app into demo videos, interactive walkthroughs, and marketing captures via one command. Enables AI agents to show their work with regenerated demos on every PR.6 npm7MIT
- AlicenseNot gradedqualityDmaintenanceEnables users to create subtitled tutorial videos by scripting browser interactions with Playwright, outputting MP4 with burned-in captions and SRT file.4MIT
- AlicenseAqualityBmaintenanceRecords narrated walkthroughs of any webapp by orchestrating Playwright, speech-mcp TTS, and FFmpeg composition.62MIT