Screen Recorder MCP

السجل الرسمي البحث والويب

Record a real browser page and cut it into a publishable vertical video. Local, no cloud.

التثبيت

أضف هذا إلى إعدادات MCP في عميلك (Claude Desktop: claude_desktop_config.json، وCursor: ‏.cursor/mcp.json، ويستخدم VS Code وغيره الصيغة نفسها «mcpServers»).

NPM package screenrec-agent
Claude Code
claude mcp add screen-recorder-mcp -- npx -y screenrec-agent@0.1.3
إعداد JSON (Claude Desktop وCursor وVS Code)
{
    "mcpServers": {
        "screen-recorder-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "screenrec-agent@0.1.3"
            ]
        }
    }
}

التوثيق

مأخوذ من ملف README للمشروع على GitHub ويُحدَّث أسبوعيًا. تفتح الروابط على GitHub.

المحتويات
  1. Screen Recorder MCP
  2. Why this exists
  3. Tools
  4. Install
  5. The one gesture Chrome insists on
  6. Requirements
  7. Roadmap
  8. License

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

ToolWhat it does
recorder_statusrecording state, bytes, bridge status
recorder_startstart recording a tab (Chrome requires one human click — see below)
recorder_stopstop and save to Downloads
recorder_fileslist recent recordings
compose_clipthe 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

  1. Download screenrec-agent-v0.1.0-win64.zip from Releases
  2. Unzip anywhere (e.g. D:\ScreenRecAgent)
  3. Add to your MCP client config:
{
  "mcpServers": {
    "screen-recorder": {
      "command": "D:\\ScreenRecAgent\\screenrec-agent.exe"
    }
  }
}
  1. screenrec-agent.exe --selftest to 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.

الأسئلة الشائعة

ما هو Screen Recorder MCP؟

Record a real browser page and cut it into a publishable vertical video. Local, no cloud.

كيف أثبّت Screen Recorder MCP؟

يعمل على جهازك. في Claude Code: claude mcp add screen-recorder-mcp -- npx -y screenrec-agent@0.1.3. وفي العملاء الآخرين، الصق إعداد JSON من هذه الصفحة في إعدادات MCP الخاصة بهم.

هل يحتاج Screen Recorder MCP إلى مفتاح API؟

لا يذكر إدراجه في السجل أي مفتاح أو سر إلزامي. قد تتطلب بعض الميزات حسابًا لدى الخدمة التي يتصل بها.

هل Screen Recorder MCP مفتوح المصدر؟

شيفرته علنية على GitHub، لكن المستودع لا يعلن ترخيصًا قياسيًا.

من يصون Screen Recorder MCP؟

ينشره Robert0303-C. يدرجه AI.tn لكنه لا يصونه ولا يوصي به.

من سجل MCP الرسمي. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك.