MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
제작자가 쓴 설명(영어 원문)
Turn YouTube product demos into structured UX flow reports, and compare demos side by side.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
FLOWSCOPE_API_URL, FLOWSCOPE_API_TOKEN, FLOWSCOPE_MAX_WAIT비밀로 표시된 값은 내 계정의 열쇠예요. 절대 다른 사람과 공유하거나 채팅에 붙여 넣지 마세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"flowscope": {
"command": "uvx",
"args": [
"flowscope-mcp"
],
"env": {
"FLOWSCOPE_API_URL": "your-value",
"FLOWSCOPE_API_TOKEN": "your-value",
"FLOWSCOPE_MAX_WAIT": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add flowscope --env FLOWSCOPE_API_URL=your-value --env FLOWSCOPE_API_TOKEN=your-value --env FLOWSCOPE_MAX_WAIT=your-value -- uvx flowscope-mcp실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"flowscope": {
"command": "uvx",
"args": [
"flowscope-mcp"
],
"env": {
"FLOWSCOPE_API_URL": "your-value",
"FLOWSCOPE_API_TOKEN": "your-value",
"FLOWSCOPE_MAX_WAIT": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"flowscope": {
"type": "stdio",
"command": "uvx",
"args": [
"flowscope-mcp"
],
"env": {
"FLOWSCOPE_API_URL": "your-value",
"FLOWSCOPE_API_TOKEN": "your-value",
"FLOWSCOPE_MAX_WAIT": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
FLOWSCOPE_API_URL envFLOWSCOPE_MAX_WAIT env이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리 이름이 GitHub 계정 DavidNgugi 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
입력해야 할 값: FLOWSCOPE_API_TOKEN
내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.1.1)은 30일 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Python (uv)도 있어야 해요.
같은 카테고리에는: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
An MCP server that exposes the FlowScope UX-analysis pipeline to any LLM client. Speaks MCP protocol 2026-07-28 and ships two spec-portable Agent Skills.
uvx flowscope-mcp # stdio server; needs a local FlowScope backend
FlowScope takes a YouTube product-demo URL, downloads the video, transcribes it, extracts and de-duplicates screenshots of each distinct screen, describes every screen with a vision model, and synthesises a step-by-step UX flow. This package turns that pipeline into tools an agent can call.
Ask your agent something like:
Compare the onboarding flows in these two videos:
and
Tear down the checkout UX in this demo:
This server is a client of a running FlowScope backend; it does not run the pipeline itself. Start the backend first:
cd backend
uvicorn app.main:app --port 8000
The backend needs ffmpeg, a Python environment with backend/requirements.txt, and one LLM provider key in backend/.env. The server's flowscope_health_check tool reports exactly which of these is missing, so you can ask your agent to check rather than guessing.
One step, and it brings the skills, the prompts, and the server registration:
/plugin marketplace add DavidNgugi/flowscope
/plugin install flowscope@flowscope
Nothing needs a permanent install — uvx runs it in a throwaway environment. uv is the only prerequisite (brew install uv):
uvx flowscope-mcp # starts a stdio server
uvx flowscope-mcp --version # confirm the published version uvx flowscope-mcp@0.1.0 # pin, when reproducibility matters
uvx --from /absolute/path/to/flowscope/mcp flowscope-mcp
uvx --from "git+https://github.com/DavidNgugi/flowscope.git@main#subdirectory=mcp" flowscope-mcp
| Variable | Default | Purpose |
|---|---|---|
FLOWSCOPE_API_URL | http://127.0.0.1:8000 | Backend base URL. /api is appended if absent, so either form works. |
FLOWSCOPE_API_TOKEN | _(empty)_ | Sent as Authorization: Bearer …. Only needed behind an authenticating proxy. |
FLOWSCOPE_HTTP_TIMEOUT | 30 | Seconds for ordinary requests. |
FLOWSCOPE_MAX_WAIT | 900 | Default wait budget for flowscope_analyze_video. |
FLOWSCOPE_POLL_INTERVAL | 5 | Seconds between job-status polls. |
These are read from the process environment on each call. The MCP Python SDK v2 deliberately stopped reading MCP_* variables and .env files, so set them in your client's server configuration instead.
The config shapes genuinely differ — VS Code's own file uses `servers` where every other client uses `mcpServers`, Codex is TOML, and Claude Desktop does not expand ${VAR} placeholders — so generating the file is more reliable than copying a snippet:
uvx --from flowscope-mcp flowscope-mcp-install --help # every client + its path
uvx --from flowscope-mcp flowscope-mcp-install print # portable JSON, writes nothing
uvx --from flowscope-mcp flowscope-mcp-install claude-code uvx --from flowscope-mcp flowscope-mcp-install cursor uvx --from flowscope-mcp flowscope-mcp-install vscode uvx --from flowscope-mcp flowscope-mcp-install codex uvx --from flowscope-mcp flowscope-mcp-install gemini uvx --from flowscope-mcp flowscope-mcp-install claude-desktop
It merges into an existing config file and leaves other servers alone.
| Harness | File | Key | Syntax |
|---|---|---|---|
| Claude Code | .mcp.json, ~/.claude.json | mcpServers | JSON |
| Claude Desktop | claude_desktop_config.json | mcpServers | JSON |
| Cursor | .cursor/mcp.json, ~/.cursor/mcp.json | mcpServers | JSON |
| VS Code | .vscode/mcp.json | `servers` | JSON |
| Codex CLI | ~/.codex/config.toml | [mcp_servers.flowscope] | TOML |
| Gemini CLI | ~/.gemini/settings.json | mcpServers | JSON |
VS Code additionally reads the portable /.mcp.json shape (key mcpServers), which flowscope-mcp-install vscode-portable writes when you want one config shared with Claude Code and Cursor.
Remote / shared deployment
Run one server for several clients, or for a harness that cannot spawn a process:
flowscope-mcp --transport streamable-http --host 127.0.0.1 --port 8765
Clients connect to POST http://127.0.0.1:8765/mcp:
claude mcp add --transport http flowscope http://127.0.0.1:8765/mcp
docs/install.md has the full per-harness reference, the placeholder syntax each one accepts, and the two traps that most often break an install.
Restart your client, open a new chat, and check the install first:
Check whether FlowScope is ready to use.
That runs flowscope_health_check and names anything missing — usually ffmpeg or an LLM provider key on the backend host. Then ask for what you want.
One video, fully analysed
Tear down the onboarding UX in this demo:
What does this product actually do, based on this demo? Walk me through the flow screen by screen:
Analyse
and tell me where a first-time user would get stuck.
A specific question about a flow
In this demo, how many steps does signup take, and what does each one ask for?
Does this demo show any error or empty states?
What's above the fold on the first screen, and what's the primary call to action?
Several videos, compared
Compare the onboarding flows in these two demos. Where do they diverge, and what's the trade-off each one makes?
-
-
I'm designing a checkout flow. What do these two demos do differently, and what should I borrow?
Which of these three gets a new user to first value fastest, judging by the demos?
Working with what already exists
What videos has FlowScope already analysed?
Show me the screenshot of the pricing screen from that report.
You do not need to phrase these carefully. Analyses are cached by YouTube video id, so a vague prompt costs a lookup rather than a re-analysis — the agent checks the cache before spending anything.
Analysing a video downloads it, transcribes it, extracts and de-duplicates screenshots, then makes one vision call per distinct screen plus a synthesis call. A five-minute demo typically yields 15–40 screens. Expect 2–10 minutes and real money per video.
flowscope_analyze_video waits by default and usually returns the finished report directly, so one prompt is normally enough. If the video needs longer than the budget it returns status: "running" with a video_id, and the agent should poll flowscope_job_status. If it resubmits the URL instead, stop it — that starts duplicate work.
Reports have three layers: ux_insights (the synthesis), flow_steps (the ordered user path), and frames (the evidence — one entry per screen, with its purpose, UI elements, and aligned narration). A good answer leads with the insights and cites the screen behind each claim. The bundled skills enforce this, including saying "the demo does not show this" rather than inferring.
docs/usage.md has the full walkthrough, prompt patterns that produce better answers, and a troubleshooting table.
Ten tools, split between read-only inspection and actions that cost money.
| Tool | Annotations | What it does |
|---|---|---|
flowscope_health_check | read-only | Backend up? ffmpeg, yt-dlp, provider key present? |
flowscope_list_videos | read-only | Every stored video with its latest job status. |
flowscope_job_status | read-only | Progress of one analysis job. |
flowscope_get_report | read-only | The finished UX report: flow, insights, per-screen findings. |
flowscope_frame_image | read-only | The actual screenshot for one screen, as an image. |
flowscope_compare_videos | open-world | Cross-video common patterns, divergences, stage matrix. |
flowscope_analyze_video | open-world | Download and analyse one or more URLs. Costs money. |
flowscope_retry_video | idempotent | Re-queue a failed job; completed stages are reused. |
flowscope_reanalyze_video | destructive | Discard derived results and redo analysis. |
flowscope_delete_video | destructive | Remove a video; optionally delete media from disk. |
Plus two prompts (flowscope_ux_teardown, flowscope_compare_flows) and two resources (flowscope://videos, flowscope://videos/{video_id}/report).
Analysing a video downloads it, transcribes it, and makes one vision call per distinct screen plus a synthesis call. That is minutes and real money per video. Two things protect against waste:
flowscope_list_videos reveals existing analyses, and resubmitting a finished video is free and instant.flowscope_analyze_video checks the cache before starting work and only submits what is actually new.The bundled skill teaches an agent to check the cache first.
flowscope-mcp # stdio (default)
flowscope-mcp --transport streamable-http --port 8765
Streamable HTTP serves POST /mcp. The SDK serves the 2026-07-28 protocol revision and the older handshake era from the same endpoint, so legacy clients work without extra configuration. Legacy clients create server-side sessions, which are stored in-process — if you run more than one worker behind a load balancer, enable sticky routing.
Two Agent Skills ship alongside the server, written to the open specification so they install into any compatible client:
| Skill | Use it when |
|---|---|
analyzing-product-demo-ux | You want a teardown of one recorded flow — how onboarding, signup, or checkout works, screen by screen. |
comparing-product-demo-ux | You want several products compared: shared conventions, real divergences, and what is worth borrowing. |
They carry the operational knowledge the tool descriptions cannot: check the health and the cache before spending money, read the synthesis rather than re-deriving it from the raw transcript, say "the demo does not show this" rather than inferring, and treat an auto-caption's product names with suspicion.
The skills and the server are independent — the skills are useful on a report you already have, and the server
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요