edu_video_gen

Instructions

Implementation Reference

• scenext_mcp/server.py:63-140 (handler)

  Primary MCP tool handler for 'gen_video'. This function is registered via @mcp.tool() decorator, validates inputs, retrieves API key from HTTP headers, and proxies the video generation request to the external Scenext API (https://api.scenext.cn/api/gen_video), returning task ID on success.

  @mcp.tool()
  async def gen_video(
      question: str = "",
      answer: str = "",
      question_images: Optional[List[str]] = None,
      answer_images: Optional[List[str]] = None,
      quality: str = DEFAULT_QUALITY
  ) -> Dict[str, Any]:
      """
      生成教学讲解视频,生成时间大约需要10到20分钟，根据题目难度来定
      
      Args:
          question: 问题内容（文本形式），question和questionImages中至少输入一个
          answer: 参考答案（文本形式）：确保生成的讲解内容准确（可选）
          question_images: 问题内容（图片形式），输入图片的URL或者base64（可选）
          answer_images: 参考答案（图片形式），输入图片的URL或者base64（可选）
          quality: 视频质量，可选值：l(低)、m(中)、h(高)，默认为配置的默认质量
      
      Returns:
          包含任务ID的字典
      """
      
      # 从请求头获取API KEY
      api_key = get_api_key_from_headers()
      
      if not api_key or api_key == "YOUR_API_KEY":
          return {"error": "请在请求头中提供有效的API Key，支持Authorization: Bearer <token>或X-API-Key: <token>"}
      
      # 验证至少有question或questionImages其中一个
      if not question.strip() and not (question_images and len(question_images) > 0):
          return {"error": "question和questionImages中至少输入一个"}
      
      url = f"{API_BASE_URL}/gen_video"
      headers = {
          "Authorization": f"Bearer {api_key}",
          "Content-Type": "application/json"
      }
  
      data = {
          "question": question,
          "answer": answer,
          "questionImages": question_images or [],
          "answerImages": answer_images or [],
          "quality": quality,
      }
  
      try:
          async with aiohttp.ClientSession() as session:
              async with session.post(url, json=data, headers=headers) as response:
                  if response.status == 200:
                      result = await response.json()
                      logger.info(f"视频生成请求成功: {result}")
                      
                      if result.get("status") == "success":
                          return {
                              "status": "success",
                              "task_id": result.get("data", {}).get("task_id"),
                              "message": "视频生成任务创建成功"
                          }
                      else:
                          return {
                              "error": "API返回错误状态",
                              "details": result
                          }
                  else:
                      error_text = await response.text()
                      logger.error(f"API请求失败: {response.status} - {error_text}")
                      return {
                          "error": f"API请求失败: {response.status}",
                          "details": error_text
                      }
      except aiohttp.ClientError as e:
          logger.error(f"网络请求错误: {e}")
          return {"error": f"网络请求错误: {str(e)}"}
      except Exception as e:
          logger.error(f"未知错误: {e}")
          return {"error": f"未知错误: {str(e)}"}

• scenext_mcp/server.py:63-63 (registration)

  Registration of the gen_video tool using FastMCP's @mcp.tool() decorator.

  @mcp.tool()

• scenext_mcp/server.py:64-82 (schema)

  Input schema defined by function parameters with type hints and detailed docstring describing arguments and return value.

  async def gen_video(
      question: str = "",
      answer: str = "",
      question_images: Optional[List[str]] = None,
      answer_images: Optional[List[str]] = None,
      quality: str = DEFAULT_QUALITY
  ) -> Dict[str, Any]:
      """
      生成教学讲解视频,生成时间大约需要10到20分钟，根据题目难度来定
      
      Args:
          question: 问题内容（文本形式），question和questionImages中至少输入一个
          answer: 参考答案（文本形式）：确保生成的讲解内容准确（可选）
          question_images: 问题内容（图片形式），输入图片的URL或者base64（可选）
          answer_images: 参考答案（图片形式），输入图片的URL或者base64（可选）
          quality: 视频质量，可选值：l(低)、m(中)、h(高)，默认为配置的默认质量
      
      Returns:
          包含任务ID的字典