Screen Recorder MCP
Record a real browser page and cut it into a publishable vertical video. Local, no cloud.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
screenrec-agentclaude mcp add screen-recorder-mcp -- npx -y screenrec-agent@0.1.3
{
"mcpServers": {
"screen-recorder-mcp": {
"command": "npx",
"args": [
"-y",
"screenrec-agent@0.1.3"
]
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
Screen Recorder MCP
Let your AI agent record a real browser page and cut it into a publishable vertical video.
An MCP server for Claude Code, Cursor, Codex and Hermes. Your agent records a page over CDP (no browser extension, no permission dialog), then composes the clip: device frame, held-frame callouts, punch-ins, captions, music with real ducking, end card.
Everything runs locally. No upload, no API key, no cloud render.
录制 → 设备框 → 冻结圈注 → 局部放大 → 字幕 → 结尾卡 → 成片
Why this exists
Every "AI video" tool generates pixels and hopes the text survives. This one doesn't generate anything: it records your actual UI and draws text with a font engine. Every digit is your real number.
The agent-facing part is the point: an agent can produce a finished clip as a tool call, not a chat suggestion.
Tools
| Tool | What it does |
|---|---|
recorder_status | recording state, bytes, bridge status |
recorder_start | start recording a tab (Chrome requires one human click — see below) |
recorder_stop | stop and save to Downloads |
recorder_files | list recent recordings |
compose_clip | the actual product: record → finished video |
compose_clip takes captions, annotations (held-frame callouts), focus (punch-ins), end_title,
music, frame (phone/browser), pip (picture-in-picture).
Install
- Download
screenrec-agent-v0.1.0-win64.zipfrom Releases - Unzip anywhere (e.g.
D:\ScreenRecAgent) - Add to your MCP client config:
{
"mcpServers": {
"screen-recorder": {
"command": "D:\\ScreenRecAgent\\screenrec-agent.exe"
}
}
}
screenrec-agent.exe --selftestto verify the install
The one gesture Chrome insists on
chrome.tabCapture needs activeTab, and activeTab only comes from invoking the extension on that tab.
No script can fake it (verified: even a trusted CDP click inside an extension page fails). So:
- Page recording (CDP) — fully autonomous, no click, no extension
- Desktop + microphone recording (extension) — the human clicks the toolbar icon once, the agent handles everything after
Requirements
- Windows 10/11 x64
- ~300 MB disk
- An MCP client
Roadmap
- [x] CDP recording, freeze-frame callouts, punch-ins
- [x] Device frame, captions, end card, music ducking, picture-in-picture
- [ ] Voice-over (piper, EN + ZH) — Full edition
- [ ] macOS
License
Commercial. Source available for review; redistribution of the packaged binary is not permitted.
Frequently asked questions
What is Screen Recorder MCP?
Record a real browser page and cut it into a publishable vertical video. Local, no cloud.
How do I install Screen Recorder MCP?
It runs on your machine. In Claude Code: claude mcp add screen-recorder-mcp -- npx -y screenrec-agent@0.1.3. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Screen Recorder MCP need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is Screen Recorder MCP open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains Screen Recorder MCP?
It is published by Robert0303-C. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.