{
  "markdown": "# MiniMax H3 MCP\n\n<!-- mcp-name: io.github.AceDataCloud/mcp-minimax -->\n\n[![PyPI](https://img.shields.io/pypi/v/mcp-minimax.svg)](https://pypi.org/project/mcp-minimax/)\n[![Python](https://img.shields.io/badge/python-3.10+-blue.svg)](https://python.org)\n[![License](https://img.shields.io/badge/license-MIT-yellow.svg)](LICENSE)\n\nModel Context Protocol server for MiniMax H3 multimodal video generation through AceDataCloud.\n\n## Capabilities\n\n- Text-to-video\n- Image-, video-, and audio-guided video generation\n- 4–15 second output in 768P or 2K, with adaptive, landscape, portrait, and square ratios\n- Optional asynchronous submission, task retrieval, batch retrieval, and deletion\n- Hosted OAuth HTTP transport and local stdio transport\n\n## Tools\n\n| Tool | Purpose |\n| --- | --- |\n| `minimax_generate_video_from_text` | Generate from a detailed prompt |\n| `minimax_generate_video_from_images` | Generate from one to nine image URLs |\n| `minimax_generate_video_from_audio` | Generate with one to three audio URLs and required images |\n| `minimax_generate_video` | Generate from the full documented content schema |\n| `minimax_list_tasks` | List tasks with optional timestamp filters |\n| `minimax_get_task` | Retrieve one task |\n| `minimax_get_tasks_batch` | Retrieve several tasks |\n| `minimax_delete_task` | Delete one task |\n| `minimax_list_models` | Show model constraints |\n| `minimax_list_actions` | Show available workflows |\n\n## Hosted server\n\n```text\nhttps://minimax.mcp.acedata.cloud/mcp\n```\n\nThe hosted server supports AceDataCloud OAuth. MCP clients that support remote OAuth can connect directly to this URL.\n\nPublic API reference: [MiniMax H3 Videos API](https://platform.acedata.cloud/documents/minimax-videos).\n\n## Local installation\n\n```bash\npipx install mcp-minimax\nexport ACEDATACLOUD_API_TOKEN=\"YOUR_API_TOKEN\"\nmcp-minimax\n```\n\nGet a token from [AceDataCloud](https://platform.acedata.cloud/console/applications).\n\n### Claude Code\n\n```bash\nclaude mcp add minimax --transport stdio \\\n  --env ACEDATACLOUD_API_TOKEN=YOUR_API_TOKEN \\\n  -- mcp-minimax\n```\n\n### Generic MCP configuration\n\n```json\n{\n  \"mcpServers\": {\n    \"minimax\": {\n      \"command\": \"mcp-minimax\",\n      \"env\": {\n        \"ACEDATACLOUD_API_TOKEN\": \"YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n## Examples\n\nText:\n\n```text\nGenerate a 6-second 16:9 video: a red fox running through a snowy forest at dawn, low tracking shot.\n```\n\nImages:\n\n```text\nAnimate these two reference images for 8 seconds while preserving the character and clothing.\n```\n\nAudio:\n\n```text\nCreate a 9:16 dance video guided by this audio, with cuts and motion following the beat.\n```\n\nThe HTTP API waits for completion by default, while MCP generation tools default `async` to `true` so agents receive a task ID immediately. Poll it with `minimax_get_task` until the final AceDataCloud CDN video is available. Set `async=false` only when the client can safely wait for the complete result.\n\n## Development\n\n```bash\npip install -e \".[dev,test]\"\nruff check .\npytest --cov=core --cov=tools\nmypy core tools\n```\n\n## Documentation\n\n<!-- canonical-documentation -->\n[Documentation](https://platform.acedata.cloud/documents/minimax-videos)\n\n## License\n\nMIT\n",
  "bytes": 3195,
  "sha": "de7aad6707e68524708f293828422c5fff24df07fac47d60dd6bcba6925cd11d",
  "repo_slug": "acedatacloud/minimaxmcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_acedatacloud_mcp_minimax_09f4dd8b/readme"
}