{
  "markdown": "# @vidalytics/mcp\n\n[![npm version](https://img.shields.io/npm/v/@vidalytics/mcp)](https://www.npmjs.com/package/@vidalytics/mcp)\n[![CI](https://github.com/vidalytics/vidalytics-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/vidalytics/vidalytics-mcp/actions/workflows/ci.yml)\n[![license](https://img.shields.io/npm/l/@vidalytics/mcp)](LICENSE)\n\nOne-command setup that connects your AI coding assistant to Vidalytics video analytics data via the [Model Context Protocol](https://modelcontextprotocol.io).\n\nWorks with Claude (CLI & Desktop), Windsurf, Cursor, and any other MCP-compatible client.\n\n## Setup\n\n```bash\nnpx @vidalytics/mcp install\n```\n\nThat's it. The installer detects which AI clients you have installed, lets you **pick which ones to configure**, and wires them up. Restart the client — a browser window will open for OAuth authorization on first use.\n\n## Cursor\n\n[![Add Vidalytics to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=vidalytics&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLnZpZGFseXRpY3MuY29tL3B1YmxpYy92MS9tY3AifQ%3D%3D)\n\n**Or via the installer:**\n\n```bash\nnpx @vidalytics/mcp install --client cursor\n```\n\n**Or manually** — add this to `~/.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"vidalytics\": {\n      \"url\": \"https://api.vidalytics.com/public/v1/mcp\"\n    }\n  }\n}\n```\n\nRestart Cursor. On first use a browser window opens for OAuth authorization with your Vidalytics account — no API key or environment variables to set.\n\n## What it does\n\n- Detects installed MCP clients (Claude CLI, Claude Desktop, Windsurf, Cursor) by checking config files, app directories, binaries in `$PATH`, and app bundles (e.g. `/Applications` on macOS)\n- Presents an interactive checklist (detected clients pre-selected) so you configure exactly the ones you want — or pick them non-interactively with `--client`\n- Adds Vidalytics as an MCP server in each selected client's config\n- Verifies after writing: the config is valid and the MCP server is reachable\n- Non-interactive terminals (CI) and any explicit selection flag (`--client`, `--all`, `--yes`) skip the checklist and behave predictably\n\n## Available tools\n\nOnce connected, your AI assistant gains access to:\n\n| Tool | Description |\n|------|-------------|\n| `set_user_context` | MUST be called before any other tool to enable analytics |\n| `list_videos` | List videos with pagination |\n| `get_video` | Get video details |\n| `get_video_by_embed_guid` | Find a video by its embed GUID |\n| `update_video` | Update a video's title or folder |\n| `get_video_embed` | Get the embed code and configuration |\n| `get_video_settings` | Get playback settings (autoplay, controls, etc) |\n| `get_video_thumbnail` | Get the thumbnail image URL |\n| `get_video_stats` | Views, play rate, watch time, conversions |\n| `get_video_dropoff` | Audience retention by percentage |\n| `get_video_percentage_watched` | % of viewers who reached each point |\n| `get_video_live_metrics` | Real-time active viewers and watch rate |\n| `get_video_ctas` | Get CTAs for a video |\n| `get_video_pause_screens` | Get pause screens for a video |\n| `get_videos_stats_batch` | Stats for up to 30 videos at once |\n| `get_videos_timeline` | Timeline stats for up to 5 videos |\n| `list_folders` | List video folders |\n| `list_settings_templates` | List settings templates |\n| `get_api_usage` | Get current API usage and quota |\n| `list_connections` | List apps connected to your account |\n| `revoke_connection` | Disconnect an app or yourself |\n| `upload_video_from_url` | Upload a video from a remote URL |\n| `get_video_upload_url` | Get a signed URL for local file upload |\n| `validate_upload` | Complete a direct video upload |\n| `publish_video` | Publish a video's pending draft settings |\n| `duplicate_video` | Duplicate a video and publish the copy |\n| `create_folder` | Create a video folder, optionally nested under another folder |\n| `apply_settings_template` | Apply a reusable player settings template to a video |\n| `create_video_cta` | Create a call-to-action on a video |\n| `update_video_cta` | Update an existing call-to-action on a video |\n| `set_video_thumbnail_from_url` | Set a video's thumbnail from a public image URL |\n| `set_video_thumbnail_from_frame` | Set a video's thumbnail from one of its frames |\n| `delete_video_thumbnail` | Remove a custom thumbnail and restore the default |\n\n## Options\n\n```\nnpx @vidalytics/mcp install [flags]\n\n  --client <names>   Configure only these clients, comma-separated\n                     (claude-cli, claude-desktop, windsurf, cursor)\n  --all              Configure all known clients, even if not detected\n  --config <path>    Also configure a custom config file (repeatable)\n  --force            Re-apply even if already configured\n  --yes              Skip prompts (configure detected clients)\n```\n\nRun with no flags in an interactive terminal to get a checklist of clients to configure (detected ones are pre-selected; use space to toggle, enter to confirm). `--client cursor,windsurf` does the same selection non-interactively.\n\nThe `--config` flag can be repeated for multiple files. The target file must follow the `{ \"mcpServers\": {} }` format used by Claude Desktop, Cursor, and Windsurf — useful for unsupported clients like Zed or VS Code with an MCP plugin.\n\n## Troubleshooting\n\n**Authorization issues, or need to re-authenticate?** Reset the credentials that\n`mcp-remote` caches in your home directory, then restart the client:\n\n| OS | Command |\n|----|---------|\n| macOS / Linux | `rm -rf ~/.mcp-auth` |\n| Windows (CMD) | `rd /s /q \"%USERPROFILE%\\.mcp-auth\"` |\n| Windows (PowerShell) | `Remove-Item -Recurse -Force \"$HOME\\.mcp-auth\"` |\n\n## MCP Registry\n\nThis server is published to the official [MCP Registry](https://registry.modelcontextprotocol.io) as **`com.vidalytics/mcp`**. It is a remote (streamable-http) server, so registry-aware MCP clients can connect to it directly at:\n\n```\nhttps://api.vidalytics.com/public/v1/mcp\n```\n\nNo API key or environment variables are required — authorization is handled via OAuth on first use.\n\n## Requirements\n\n- Node.js 18+\n- A Vidalytics account\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 6193,
  "sha": "96c039e5b9a17eafd98a20e440fedb432557acb8ca3ad30cda84978b85944e74",
  "repo_slug": "vidalytics/vidalytics-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_vidalytics_mcp_2c289971/readme"
}