# FlowScope UX Flow Analyser MCP server

> Converts YouTube product demos into structured UX flow reports and enables side-by-side comparison of user experiences.

- Repository: https://github.com/DavidNgugi/flowscope
- Page: https://hostedmcp.org/servers/davidngugi/flowscope
- Transport: stdio
- Stars: 2
- License: MIT
- Latest version: 0.1.1

## Install

### Claude Code

```sh
claude mcp add --env 'FLOWSCOPE_API_TOKEN=<YOUR_FLOWSCOPE_API_TOKEN>' flowscope -- uvx flowscope-mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "flowscope": {
      "command": "uvx",
      "args": [
        "flowscope-mcp"
      ],
      "env": {
        "FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "flowscope": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "flowscope-mcp"
      ],
      "env": {
        "FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"flowscope","type":"stdio","command":"uvx","args":["flowscope-mcp"],"env":{"FLOWSCOPE_API_TOKEN":"<YOUR_FLOWSCOPE_API_TOKEN>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "flowscope": {
      "command": "uvx",
      "args": [
        "flowscope-mcp"
      ],
      "env": {
        "FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add flowscope --env 'FLOWSCOPE_API_TOKEN=<YOUR_FLOWSCOPE_API_TOKEN>' -- uvx flowscope-mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.flowscope]
command = "uvx"
args = ["flowscope-mcp"]

[mcp_servers.flowscope.env]
FLOWSCOPE_API_TOKEN = "<YOUR_FLOWSCOPE_API_TOKEN>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'FLOWSCOPE_API_TOKEN=<YOUR_FLOWSCOPE_API_TOKEN>' flowscope uvx -- flowscope-mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "flowscope": {
      "command": "uvx",
      "args": [
        "flowscope-mcp"
      ],
      "env": {
        "FLOWSCOPE_API_TOKEN": "<YOUR_FLOWSCOPE_API_TOKEN>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `FLOWSCOPE_API_TOKEN` | no | yes | Bearer token, only needed when the backend sits behind an authenticating proxy. |
| `FLOWSCOPE_API_URL` | no | no | Base URL of the running FlowScope backend. '/api' is appended if absent. |
| `FLOWSCOPE_MAX_WAIT` | no | no | Default seconds that flowscope_analyze_video waits for a job before returning a job id. |

## Tools (10)

- `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`

## FAQ

### 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.
