SoraMCP
# SoraMCP (retired)
<!-- mcp-name: io.github.AceDataCloud/mcp-sora -->
The AceDataCloud Sora integration is retired. Its hosted MCP server and public
Sora API endpoints are no longer offered. Installing an older package does not
restore access to the retired service.
This directory retains historical source for existing integrations and reference.
Its tool definitions and examples describe the former API, not currently available
capabilities. Do not configure a new connection to `sora.mcp.acedata.cloud`.
For a supported video workflow, choose a currently published service such as
[Seedance](https://platform.acedata.cloud/documents/seedance-mcp),
[Veo](https://platform.acedata.cloud/documents/veo-mcp), or
[Kling](https://platform.acedata.cloud/documents/kling).
Check the selected service's current models, input requirements and pricing;
Sora prompts, character references, durations and task IDs are not interchangeable.
Historical tasks are not automatically migrated to another service. Preserve any
previously downloaded media and avoid resubmitting a retired task as a new generation.
## Historical source development
Offline compatibility tests can be run with `pytest -m "not integration"`.
No deployment or endpoint reactivation is included in this repository's retirement.
## License
MIT License — see [LICENSE](LICENSE).
TDQS
Scored across 10 tools
Each generation tool targets a distinct input method (text, image, character, v2) and synchronous/asynchronous modes are clearly separated. Descriptions explicitly note differences, so an agent can easily select the appropriate tool.
All tools follow a consistent sora_verb_noun pattern in snake_case (e.g., sora_generate_video, sora_get_task). The version suffixes (_v2) are appended uniformly, maintaining predictability.
With 10 tools, the set is well-scoped for a video generation service. It covers generation variants, status checks, and listing actions/models without being bloated or too sparse.
The tool surface covers generation, status retrieval (single and batch), and informational queries. A minor gap is the lack of a cancellation tool for pending tasks, but it's not critical for core workflows.