Pagecast MCP Server

Record any browser page as GIF or video via MCP

Local serverstdio

What is the Pagecast MCP server?

Most browser automation work still happens through a UI a human drives. Pagecast MCP server moves it into the conversation instead. Record any browser page as GIF or video via MCP.

The short version

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.

The tools it exposes

The server publishes 9 tools. What each one is for:

  • record_page — Open a URL, start recording. Auto-injects cursor highlight + click ripple
  • interact_page — scroll, click, hover, type, press keys, select, navigate, waitForSelector — all captured with bounding boxes
  • stop_recording — Stop 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_gif — WebM → optimized GIF (ffmpeg two-pass palette, configurable FPS/width/trim)
  • convert_to_mp4 — WebM → MP4 (H.264, ready for social/sharing/embedding)
  • record_and_export — All-in-one: record → auto-export to GIF or MP4 based on platform
  • list_recordings — List all .webm, .gif, and .mp4 files in output directory

Getting it running

Installation goes through your MCP client rather than a global install: point it at @mcpware/pagecast on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pagecast's toolset — record_page, interact_page, stop_recording and 6 more — is a fair guide to whether it matches your workflow. It is maintained by mcpware; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pagecast's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Pagecast.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available 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_export**Tooltip overlay** — magnified tooltip close-up on each interaction
cinematic_export**Cinematic 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

How to install the Pagecast MCP server

{
  "mcpServers": {
    "pagecast": {
      "command": "npx",
      "args": ["-y", "@mcpware/pagecast"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Pagecast to record page.
  • Use Pagecast to interact page.
  • Use Pagecast to stop recording.

Frequently asked questions

It connects Pagecast to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (record_page, interact_page, stop_recording, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Pagecast directly.