Converts YouTube product demos into structured UX flow reports and enables side-by-side comparison of user experiences.
Also known as DavidNgugi/flowscope, flowscope, flowscope-mcp
- Stars
- 2
- Tools
- 10
- Downloads, 30 days
- —
- Latest version
- 0.1.1
- Last commit
- Oct 12, 2026
- License
- MIT
What is FlowScope UX Flow Analyser MCP?
FlowScope UX Flow Analyser converts YouTube product demos into structured UX flow reports and enables side-by-side comparison of user experiences. It exposes 10 tools, such as flowscope_health_check, flowscope_list_videos, flowscope_job_status.
Summary generated from the project's README
About FlowScope UX Flow Analyser MCP server
FlowScope UX Flow Analyser provides a specialized pipeline for turning YouTube product demonstrations into structured user experience reports. It is designed for product designers and researchers who need to extract detailed UX insights from video content. The server acts as a client to a local FlowScope backend, which handles the heavy lifting of downloading videos, transcribing audio, extracting screenshots, and using vision models to describe individual screens.
Users interact with the server through MCP-compatible clients like Claude Desktop, Cursor, or VS Code. The system includes tools for checking backend health, listing previously analyzed videos, and retrieving detailed reports that include flow steps and screen-level findings. Because the analysis process involves vision model calls and video processing, it requires a running backend with ffmpeg and an LLM provider key configured. To prevent unnecessary costs, the server caches results by YouTube video ID, allowing for instant retrieval of previously processed content.
What you can do with it
- 1Perform a UX teardownAn agent can analyze a single YouTube URL to provide a screen-by-screen breakdown of a specific user journey like onboarding or checkout.
- 2Compare multiple product flowsYou can ask an AI to identify divergences and common patterns between two or more different product demonstration videos.
- 3Verify backend readinessDevelopers can use a health check tool to identify if missing dependencies like ffmpeg or API keys are preventing the pipeline from running.
- 4Retrieve visual evidenceAn AI client can fetch specific screenshots from a generated report to show the user exactly which UI element is being discussed.
Written from the project's README. Every use case is checked against a quote from it.
How to install FlowScope UX Flow Analyser MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall FlowScope UX Flow Analyser MCP in Claude Code
$ claude mcp add --env 'FLOWSCOPE_API_TOKEN=<YOUR_FLOWSCOPE_API_TOKEN>' flowscope -- uvx flowscope-mcpInstall FlowScope UX Flow Analyser MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"flowscope": {
"command": "uvx",
"args": [
"flowscope-mcp"
],
"env": {
"FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
}
}
}
}Install FlowScope UX Flow Analyser MCP in VS Code
.vscode/mcp.json
{
"servers": {
"flowscope": {
"type": "stdio",
"command": "uvx",
"args": [
"flowscope-mcp"
],
"env": {
"FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
}
}
}
}Install FlowScope UX Flow Analyser MCP in VS Code CLI
$ code --add-mcp '{"name":"flowscope","type":"stdio","command":"uvx","args":["flowscope-mcp"],"env":{"FLOWSCOPE_API_TOKEN":"<YOUR_FLOWSCOPE_API_TOKEN>"}}'Install FlowScope UX Flow Analyser MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"flowscope": {
"command": "uvx",
"args": [
"flowscope-mcp"
],
"env": {
"FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
}
}
}
}Install FlowScope UX Flow Analyser MCP in Codex
$ codex mcp add flowscope --env 'FLOWSCOPE_API_TOKEN=<YOUR_FLOWSCOPE_API_TOKEN>' -- uvx flowscope-mcpInstall FlowScope UX Flow Analyser MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.flowscope] command = "uvx" args = ["flowscope-mcp"] [mcp_servers.flowscope.env] FLOWSCOPE_API_TOKEN = "<YOUR_FLOWSCOPE_API_TOKEN>"
Install FlowScope UX Flow Analyser MCP in Gemini CLI
$ gemini mcp add -s user -e 'FLOWSCOPE_API_TOKEN=<YOUR_FLOWSCOPE_API_TOKEN>' flowscope uvx -- flowscope-mcpInstall FlowScope UX Flow Analyser MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"flowscope": {
"command": "uvx",
"args": [
"flowscope-mcp"
],
"env": {
"FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
}
}
}
}FlowScope UX Flow Analyser MCP tools 10
Detected from the READMEflowscope_health_checkflowscope_list_videosflowscope_job_statusflowscope_get_reportflowscope_frame_imageflowscope_compare_videosflowscope_analyze_videoflowscope_retry_videoflowscope_reanalyze_videoflowscope_delete_video
| flowscope_health_check | — | |
| flowscope_list_videos | — | |
| flowscope_job_status | — | |
| flowscope_get_report | — | |
| flowscope_frame_image | — | |
| flowscope_compare_videos | — | |
| flowscope_analyze_video | — | |
| flowscope_retry_video | — | |
| flowscope_reanalyze_video | — | |
| flowscope_delete_video | — |
Configuration
FLOWSCOPE_API_TOKENSecretBearer token, only needed when the backend sits behind an authenticating proxy.
FLOWSCOPE_API_URLBase URL of the running FlowScope backend. '/api' is appended if absent.
FLOWSCOPE_MAX_WAITDefault seconds that flowscope_analyze_video waits for a job before returning a job id.
| Name | Description | |
|---|---|---|
| FLOWSCOPE_API_TOKEN | Bearer token, only needed when the backend sits behind an authenticating proxy. | Secret |
| FLOWSCOPE_API_URL | Base URL of the running FlowScope backend. '/api' is appended if absent. | |
| FLOWSCOPE_MAX_WAIT | Default seconds that flowscope_analyze_video waits for a job before returning a job id. |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachabledavidngugi/flowscope is public and reachablegithub.com/davidngugi/flowscope ↗Pass
- Package names this repository as its sourceflowscope-mcp names davidngugi/flowscope as sourcepypi.org/project/flowscope-mcp/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-12github.com/davidngugi/flowscope ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from flowscope-mcpPass
- No critical advisory in the package or its dependencies29 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model10 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubflowscope-mcp
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:
<url>and<url>
Tear down the checkout UX in this demo:
<url>
Requirements
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.
Install
As a Claude Code plugin
One step, and it brings the skills, the prompts, and the server registration:
/plugin marketplace add DavidNgugi/flowscope
/plugin install flowscope@flowscope
From PyPI
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
From a git URL or a local checkout
uvx --from /absolute/path/to/flowscope/mcp flowscope-mcp
uvx --from "git+https://github.com/DavidNgugi/flowscope.git@main#subdirectory=mcp" flowscope-mcp
Environment
| 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.
Point a harness at it
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 <project>/.mcp.json shape (key
mcpServers), which flowscope-mcp-install vscode-portable writes when you want
one config shared with Claude Code and Cursor.
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.
Use it
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.
Example prompts
One video, fully analysed
Tear down the onboarding UX in this demo:
<youtube-url>
What does this product actually do, based on this demo? Walk me through the flow screen by screen:
<youtube-url>
Analyse
<youtube-url>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?
<youtube-url>
Does this demo show any error or empty states?
<youtube-url>
What's above the fold on the first screen, and what's the primary call to action?
<youtube-url>
Several videos, compared
Compare the onboarding flows in these two demos. Where do they diverge, and what's the trade-off each one makes?
<youtube-url-1><youtube-url-2>
I'm designing a checkout flow. What do these two demos do differently, and what should I borrow?
<url1><url2>
Which of these three gets a new user to first value fastest, judging by the demos?
<url1><url2><url3>
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.
What happens after you press enter
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.
Answers are grounded, or should be
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.
Tools
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).
Cost and time
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:
- Results are cached by YouTube video id.
flowscope_list_videosreveals existing analyses, and resubmitting a finished video is free and instant. flowscope_analyze_videochecks the cache before starting work and only submits what is actually new.
The bundled skill teaches an agent to check the cache first.
Transports
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.
Skills
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 works without them.
Install them
With the plugin (Claude Code) — skills and server in one step:
/plugin marketplace add DavidNgugi/flowscope
/plugin install flowscope@flowscope
The portable directory, which most clients scan. .agents/skills/ is the
cross-client project convention, so several harnesses pick it up from one copy:
mkdir -p .agents/skills && cp -r skills/* .agents/skills/ # this project
mkdir -p ~/.agents/skills && cp -r skills/* ~/.agents/skills/ # every project
A client's own directory, when you want it only there:
cp -r skills/* ~/.claude/skills/ # Claude Code, personal scope
cp -r skills/* ~/.codex/skills/ # Codex CLI
cp -r skills/* ~/.cursor/skills/ # Cursor
cp -r skills/* .github/skills/ # VS Code / Copilot
cp -r skills/* ~/.gemini/skills/ # Gemini CLI
With the skills CLI, for a team or one of ~80 agent targets:
npx skills add DavidNgugi/flowscope
| Client | Project | Personal |
|---|---|---|
| Claude Code | .claude/skills/ |
~/.claude/skills/ |
| Codex CLI | .agents/skills/ |
~/.codex/skills/ |
| Cursor | .agents/skills/, .cursor/skills/ |
~/.cursor/skills/ |
| VS Code / Copilot | .github/skills/, .claude/skills/, .agents/skills/ |
~/.copilot/skills/ |
| Gemini CLI | .gemini/skills/ or .agents/skills/ |
~/.gemini/skills/ |
| Zed, Cline | .agents/skills/ |
~/.agents/skills/ |
Verify a skill is portable with the official validator:
pip install "git+https://github.com/agentskills/agentskills.git#subdirectory=skills-ref"
skills-ref validate .agents/skills/analyzing-product-demo-ux
# -> Valid skill: .agents/skills/analyzing-product-demo-ux
Both skills declare only the six fields the open specification defines, so they work unmodified in Claude Code, Claude Desktop, ChatGPT and Codex, Cursor, VS Code, Gemini CLI, Zed, Goose, OpenCode and the rest. A test enforces that.
docs/skills.md covers every route, the compatibility aliases each client reads, and how to use the skills without the MCP server at all.
Documentation
| Document | Contents |
|---|---|
| docs/install.md | Installing into each harness: config shapes, placeholder syntax, remote/HTTP setup, verification |
| docs/usage.md | Example prompts, what happens on each call, troubleshooting, getting better answers |
| docs/skills.md | Installing the skills into each client, the directory matrix, and using them without the server |
| docs/server-internals.md | Design rationale: annotations, error handling, protocol era, output shapes |
| docs/publishing.md | Releasing: tag or manual, versioning rules, one-time setup, recovery |
| docs/security.md | Tool poisoning, data flow, and what a non-sandboxed server means |
Releasing
Releases are automated and driven by version tags. .github/workflows/release.yml
verifies everything, publishes to PyPI with trusted publishing, publishes to the
MCP Registry, and creates a GitHub release with the wheel and sdist attached.
cd mcp
./.venv/bin/python scripts/version.py bump 0.2.0 # rewrites all five files
cd ..
git commit -am "release: v0.2.0" && git tag -a v0.2.0 -m "v0.2.0"
git push && git push --tags
Publishing also runs on demand — Actions → Release MCP server — with a
publish input that defaults to off, so the default manual run verifies and
builds without publishing anything.
Six version declarations in five files must agree, and the MCP Registry requires
the server and its package version to match. scripts/version.py is what keeps
them in sync, because editing them by hand is how a release fails during
publishing — and PyPI permanently refuses to reuse a version number, so a
half-published release cannot be retried:
python scripts/version.py show # what every file currently says
python scripts/version.py check # fail if any disagree, including the tag
See docs/publishing.md for the full release process, version-numbering rules, the one-time PyPI configuration, and what to do when a release goes wrong.
Development
cd mcp
python3 -m venv .venv && ./.venv/bin/pip install -e ".[dev]"
./.venv/bin/ruff check src tests scripts
./.venv/bin/pytest -q
The suite is offline: tool behaviour runs against an in-memory MCP client and a mocked HTTP transport, so it needs neither a network nor a running backend. Separate tests spawn the real process to verify the stdio contract — that stdout carries only protocol frames — and validate the registry, plugin, and version metadata. The release workflow's triggers are pinned by tests too, so a future edit cannot make publishing automatic on a branch push.
Validate the skills and manifests against the official tooling:
skills-ref validate skills/analyzing-product-demo-ux # agentskills.io reference validator
claude plugin validate . # marketplace manifest
claude plugin validate ./mcp --strict # plugin manifest
python scripts/validate_metadata.py # server.json + wheel contents
Licence
MIT
FlowScope UX Flow Analyser MCP questions
How do I add FlowScope UX Flow Analyser MCP to Claude Code?
Run claude mcp add --env 'FLOWSCOPE_API_TOKEN=<YOUR_FLOWSCOPE_API_TOKEN>' flowscope -- uvx flowscope-mcp in your terminal. Add --scope user to make it available in every project.
How do I add FlowScope UX Flow Analyser MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does FlowScope UX Flow Analyser MCP provide?
It exposes 10 tools, including flowscope_health_check, flowscope_list_videos, flowscope_job_status, flowscope_get_report, flowscope_frame_image.
Does this server run the analysis pipeline itself?
No, this server acts as a client to a running FlowScope backend which performs the actual processing.
How much does it cost to analyze a video?
Analysis involves downloading, transcribing, and making vision calls for each distinct screen, which incurs real-world costs and takes 2–10 minutes.
How can I check if the server is set up correctly?
You can use the flowscope_health_check tool to verify if the backend is up and if required components like ffmpeg or LLM keys are present.