Panda Video MCP Server

MCP (Model Context Protocol) server for the Panda Video API.

131 tools covering the full Panda Video API — videos, folders, playlists, profiles, lives, analytics, funnels, watermark, AI features, and more.

Quick Start

Install via npx (recommended)

PANDA_API_KEY=your-key npx @panda-video/mcp

Install globally

npm install -g @panda-video/mcp
PANDA_API_KEY=your-key panda-video-mcp

Install via Smithery

npx -y @smithery/cli install @panda-video/mcp --client claude

Requirements

• Node.js 18+
• Panda Video API Key (Settings → Integrations → API Key)

Connecting to MCP Clients

Claude Desktop (stdio — one-line config)

Edit claude_desktop_config.json:

{
  "mcpServers": {
    "panda-video": {
      "command": "npx",
      "args": ["-y", "@panda-video/mcp"],
      "env": { "PANDA_API_KEY": "your-key" }
    }
  }
}

Claude Code

claude mcp add panda-video -- npx -y @panda-video/mcp

Then set the env var PANDA_API_KEY in your shell or .claude/settings.json.

Cursor / Windsurf (HTTP mode)

Run the HTTP server:

PANDA_API_KEY=your-key npx @panda-video/mcp --http
# or
npm run start:http

Then add http://localhost:3000/mcp in your MCP settings.

Claude Desktop / Gemini CLI (HTTP)

{
  "mcpServers": {
    "panda-video": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Development

From source

git clone https://github.com/pandavideo/panda-video-mcp.git
cd panda-video-mcp
npm install
npm run build

export PANDA_API_KEY=your-panda-video-api-key-here
npm start           # stdio mode
npm run start:http  # HTTP mode (port 3000)
npm run dev         # stdio dev (tsx)
npm run dev:http    # HTTP dev (tsx)

Architecture

src/
├── index.ts              # Stdio entry point
├── server.ts             # HTTP/Express entry point
├── client.ts             # pandaFetch() + auth + rate limiter
├── utils/
│   ├── errors.ts         # PandaApiError + withErrorHandling wrapper
│   ├── schemas.ts        # Shared Zod schemas (pagination, date, hex color)
│   ├── rate-limiter.ts   # Token bucket rate limiter (60 req/min)
│   └── api-key-validator.ts  # Startup key validation
├── resources/
│   └── api-info.ts       # MCP resources (limits, tool overview)
└── tools/                # 20 domain-specific tool files
    ├── videos.ts         # 7 tools
    ├── folders.ts        # 10 tools
    ├── playlists.ts      # 8 tools
    ├── profiles.ts       # 6 tools
    ├── live.ts           # 13 tools
    ├── analytics.ts      # 14 tools
    ├── funnels.ts        # 7 tools
    ├── review.ts         # 11 tools
    ├── watermark.ts      # 14 tools
    ├── thumbnails.ts     # 2 tools
    ├── subtitles.ts      # 4 tools
    ├── custom-fields.ts  # 4 tools
    ├── webhooks.ts       # 3 tools
    ├── organization.ts   # 2 tools
    ├── users.ts          # 5 tools
    ├── downloads.ts      # 3 tools
    ├── shorts.ts         # 6 tools
    ├── ai-assistants.ts  # 8 tools
    ├── ai-dubbing.ts     # 1 tool
    ├── referrals.ts      # 3 tools
    └── misc.ts           # Barrel (re-exports all above)

Tools (131 total)

| Domain | Count | Tools | |---|---|---| | Videos | 7 | list, get, update, recover, delete, upload URL, upload m3u8 | | Folders | 10 | CRUD, library info, qualities, referer domains | | Playlists | 8 | CRUD, video management, password-protected access | | Profiles | 6 | CRUD, apply to videos (colors, autoplay, smart autoplay) | | Live | 13 | CRUD, finish, metrics, stream keys, chat CRUD | | Analytics | 14 | account, video, retention, ranking, geo, browser, referrer, realtime, live, viewers, bandwidth, billing, users, credits | | Funnels | 7 | CRUD, add/remove videos with coordinates | | Review | 11 | Review links, timestamped comments (owner + public APIs) | | Watermark/DRM | 14 | Status, groups CRUD, JWT, private tokens CRUD | | Thumbnails | 2 | get, delete | | Subtitles | 4 | get, get by language, delete, AI generate | | Custom Fields | 4 | CRUD | | Webhooks | 3 | get, set, delete | | Organization | 2 | get, update | | Users | 5 | CRUD | | Downloads | 3 | request async, check status, direct download | | Shorts | 6 | list jobs, list segments, delete, save to library, download | | AI Assistants | 8 | CRUD, video bindings, chat visibility, purchase overview | | AI Dubbing | 1 | create dubbing job | | Referrals | 3 | summary, transactions, send invites |

MCP Resources

• panda://api/limits — Rate limits, batch limits, plan constraints
• panda://api/overview — Tool listing by domain

Limits & Security

• Rate limiting: 60 requests/minute per API key (token bucket)
• Batch limits: Max 50 items per batch operation
• API key validation: Validated at startup (stdio) or on first tool call (HTTP)
• Error handling: All API errors mapped to LLM-friendly messages
• Pagination: All list endpoints support page and per_page (max 100)

Development

npm run lint          # ESLint
npm run format:check  # Prettier check
npm run format        # Prettier fix
npm test              # Vitest
npm test:watch        # Vitest watch mode
npm run build         # TypeScript compile

CI/CD

Bitbucket Pipelines runs on every push: lint → format check → build → test.

Releases are managed with semantic-release on the main branch.

License

MIT