sora_list_actions

Instructions

Reference guide for what each action does and which tool to use.
Helpful for understanding the full capabilities of the Sora MCP.

Returns:
    Categorized list of all actions and their corresponding tools.

Implementation Reference

• tools/info_tools.py:69-120 (handler)

  The actual handler function for the sora_list_actions tool. Decorated with @mcp.tool(), it returns a string listing all available Sora API actions and corresponding tools, organized by category (video generation, task management, information, workflow examples).

  @mcp.tool()
  async def sora_list_actions() -> str:
      """List all available Sora API actions and corresponding tools.
  
      Reference guide for what each action does and which tool to use.
      Helpful for understanding the full capabilities of the Sora MCP.
  
      Returns:
          Categorized list of all actions and their corresponding tools.
      """
      # Last updated: 2026-04-05
      return """Available Sora Actions and Tools:
  
  Video Generation (Version 1 - classic):
  - sora_generate_video: Create video from a text prompt (duration: 10/15/25s, size: small/large)
  - sora_generate_video_from_image: Create video from reference images (Image-to-Video)
  - sora_generate_video_with_character: Create video with a character from reference video
  - sora_generate_video_async: Create video with callback notification
  
  Video Generation (Version 2 - partner channel):
  - sora_generate_video_v2: Create video with pixel resolution (seconds: 4/8/12, size: 720x1280 etc.)
  - sora_generate_video_v2_async: Create video v2 with callback notification
  
  Task Management:
  - sora_get_task: Check status of a single generation
  - sora_get_tasks_batch: Check status of multiple generations
  
  Information:
  - sora_list_models: Show available models and their capabilities
  - sora_list_actions: Show this action reference (you are here)
  
  Workflow Examples:
  
  1. Simple Video (v1):
     sora_generate_video(prompt) → sora_get_task(task_id)
  
  2. Image-to-Video (v1):
     sora_generate_video_from_image(prompt, image_urls) → sora_get_task(task_id)
  
  3. Character-based Video (v1):
     sora_generate_video_with_character(prompt, character_url) → sora_get_task(task_id)
  
  4. Quick Video with precise resolution (v2):
     sora_generate_video_v2(prompt, seconds=8, size="1280x720") → sora_get_task(task_id)
  
  5. Async with Callback (v1 or v2):
     sora_generate_video_async(prompt, callback_url) → Wait for callback
     sora_generate_video_v2_async(prompt, callback_url) → Wait for callback
  
  Tips:
  - Video generation takes 1-2 minutes on average
  - Use async generation with callbacks for production workflows

• core/server.py:47-55 (registration)

  The FastMCP server instance (mcp) that registers the tool via the @mcp.tool() decorator on the sora_list_actions function.

  # Initialize FastMCP server
  mcp = FastMCP(
      settings.server_name,
      icons=[Icon(src="
  ", mimeType="image/png")],
      **mcp_kwargs,
  )
  
  logger.info(f"Initialized MCP server: {settings.server_name}")

• main.py:188-192 (registration)

  Registration in the HTTP server card response, listing 'sora_list_actions' with description 'List available actions'.

      {"name": "sora_get_tasks_batch", "description": "Query multiple tasks"},
      {"name": "sora_list_models", "description": "List available models"},
      {"name": "sora_list_actions", "description": "List available actions"},
  ],
  "prompts": [

• main.py:130-134 (registration)

  Startup banner printing 'sora_list_actions' as an available tool during server initialization.

  safe_print("    - sora_get_task")
  safe_print("    - sora_get_tasks_batch")
  safe_print("    - sora_list_models")
  safe_print("    - sora_list_actions")
  safe_print("")

• tools/__init__.py:1-10 (helper)

  Tools __init__.py imports info_tools module which contains the sora_list_actions handler, registering it with the MCP server.

  """Tools module for MCP Sora server."""
  
  # Import all tools to register them with the MCP server
  from tools import info_tools, task_tools, video_tools
  
  __all__ = [
      "video_tools",
      "task_tools",
      "info_tools",
  ]