{
  "markdown": "# tube-search-mcp\n\nMCP server for [Archivarix Tube Search](https://tube.archivarix.net) — search archived YouTube videos via AI assistants.\n\nSearch over 1 billion YouTube videos indexed since 2005. Find deleted videos, metadata, thumbnails, and subtitles.\n\n## Quick Start\n\n```bash\nnpx tube-search-mcp --api-key tsk_YOUR_KEY\n```\n\nOr with environment variable:\n\n```bash\nexport TUBE_API_KEY=tsk_YOUR_KEY\nnpx tube-search-mcp\n```\n\nGet your API key at [tube.archivarix.net](https://tube.archivarix.net) (Profile → API Keys).\n\n## Configuration\n\n### Claude Desktop\n\nAdd to `~/.claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"tube-search\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"tube-search-mcp\"],\n      \"env\": {\n        \"TUBE_API_KEY\": \"tsk_YOUR_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Claude Code\n\nAdd to `~/.claude/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"tube-search\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"tube-search-mcp\"],\n      \"env\": {\n        \"TUBE_API_KEY\": \"tsk_YOUR_KEY\"\n      }\n    }\n  }\n}\n```\n\n### VS Code\n\nAdd to `.vscode/mcp.json` in your project:\n\n```json\n{\n  \"servers\": {\n    \"tube-search\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"tube-search-mcp\"],\n      \"env\": {\n        \"TUBE_API_KEY\": \"tsk_YOUR_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"tube-search\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"tube-search-mcp\"],\n      \"env\": {\n        \"TUBE_API_KEY\": \"tsk_YOUR_KEY\"\n      }\n    }\n  }\n}\n```\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `search_channel` | Find all archived videos from a YouTube channel |\n| `search_videos` | Full-text search across video titles and descriptions |\n| `get_video` | Get metadata for a specific video by ID |\n| `get_subtitles` | Get transcript as readable plain text |\n| `get_summary` | Get AI-generated video summary |\n| `generate_summary` | Generate a new AI summary for a video |\n| `browse_summaries` | Browse summaries by tag, channel, or language |\n| `get_video_status_history` | View status change history of a video |\n| `get_usage` | Check your current API usage and limits |\n\n## Resources\n\n| URI | Description |\n|-----|-------------|\n| `tube://video/{videoId}` | Video metadata |\n| `tube://channel/{channelId}` | Channel info |\n| `tube://subtitles/{videoId}` | Transcript as plain text |\n| `tube://summary/{videoId}` | AI-generated summary |\n| `tube://tags` | Popular summary tags |\n\n## Prompts\n\n| Prompt | Description |\n|--------|-------------|\n| `research_video` | Comprehensive video analysis workflow |\n| `channel_overview` | Channel research and statistics |\n| `find_deleted` | Discover and analyze deleted videos |\n\n## Environment Variables\n\n| Variable | Description | Default |\n|----------|-------------|---------|\n| `TUBE_API_KEY` | API key (required) | — |\n| `TUBE_MCP_URL` | Custom MCP endpoint | `https://tube.archivarix.net/mcp` |\n\n## How It Works\n\nThis package acts as a stdio-to-HTTP proxy. It connects to the remote Archivarix Tube Search MCP server via Streamable HTTP and exposes the same tools, resources, and prompts over stdio transport for local AI clients.\n\n```\nAI Client ←(stdio)→ tube-search-mcp ←(HTTP)→ tube.archivarix.net/mcp\n```\n\n## Documentation\n\nFull documentation: [tube.archivarix.net/guide/mcp](https://tube.archivarix.net/guide/mcp)\n\n## License\n\nMIT\n",
  "bytes": 3375,
  "sha": "2fb021ccf4a5a616ecc425d37d2d68005d6956a8e1584b6b1556478920292aea",
  "repo_slug": "archivarix-com/tube-search-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_archivarix_com_tube_search_mcp_8d0ebf70/readme"
}