MCP Kling

Instructions

Implementation Reference

• src/kling-client.ts:249-269 (handler)

  Core implementation of the extend_video tool: sends POST request to Kling AI /v1/video/extension endpoint with task_id and prompt to extend existing video.

  async extendVideo(request: VideoExtensionRequest): Promise<{ task_id: string }> {
    const path = '/v1/video/extension';
    
    const body: any = {
      task_id: request.task_id,
      prompt: request.prompt,
      duration: request.duration || '5',
      mode: request.mode || 'standard',
      model_name: request.model_name || 'kling-v2-master', // V2-master is default
    };
  
    try {
      const response = await this.axiosInstance.post(path, body);
      return response.data.data;
    } catch (error) {
      if (axios.isAxiosError(error)) {
        throw new Error(`Kling API error: ${error.response?.data?.message || error.message}`);
      }
      throw error;
    }
  }

• src/kling-client.ts:56-62 (schema)

  TypeScript interface defining input parameters for video extension request.

  export interface VideoExtensionRequest {
    task_id: string;
    prompt: string;
    model_name?: 'kling-v1' | 'kling-v1.5' | 'kling-v1.6' | 'kling-v2-master';
    duration?: '5';
    mode?: 'standard' | 'professional';
  }

• src/index.ts:224-256 (registration)

  MCP tool registration in TOOLS array, including name, description, and JSON schema for input validation.

  {
    name: 'extend_video',
    description: 'Extend a video by 4-5 seconds using Kling AI. This feature allows you to continue a video beyond its original ending, generating new content that seamlessly follows from the last frame. Perfect for creating longer sequences or adding additional scenes to existing videos.',
    inputSchema: {
      type: 'object',
      properties: {
        task_id: {
          type: 'string',
          description: 'The task ID of the original video to extend (from a previous generation)',
        },
        prompt: {
          type: 'string',
          description: 'Text prompt describing how to extend the video (what should happen next)',
        },
        model_name: {
          type: 'string',
          enum: ['kling-v1', 'kling-v1.5', 'kling-v1.6', 'kling-v2-master'],
          description: 'Model version to use for extension (default: kling-v2-master)',
        },
        duration: {
          type: 'string',
          enum: ['5'],
          description: 'Extension duration (fixed at 5 seconds)',
        },
        mode: {
          type: 'string',
          enum: ['standard', 'professional'],
          description: 'Video generation mode (default: standard)',
        },
      },
      required: ['task_id', 'prompt'],
    },
  },

• src/index.ts:558-577 (handler)

  MCP server request handler (CallToolRequestSchema) that validates arguments, calls KlingClient.extendVideo, and formats response.

  case 'extend_video': {
    const extendRequest = {
      task_id: args.task_id as string,
      prompt: args.prompt as string,
      model_name: (args.model_name as 'kling-v1' | 'kling-v1.5' | 'kling-v1.6' | 'kling-v2-master' | undefined) || 'kling-v2-master',
      duration: '5' as const,
      mode: (args.mode as 'standard' | 'professional') || 'standard',
    };
  
    const result = await klingClient.extendVideo(extendRequest);
    
    return {
      content: [
        {
          type: 'text',
          text: `Video extension started successfully!\nTask ID: ${result.task_id}\n\nThe video will be extended by approximately 5 seconds.\nUse the check_video_status tool with this task ID to check the progress.`,
        },
      ],
    };
  }

• src/index.ts:227-256 (schema)

  JSON schema in tool registration for input validation in MCP protocol.

    inputSchema: {
      type: 'object',
      properties: {
        task_id: {
          type: 'string',
          description: 'The task ID of the original video to extend (from a previous generation)',
        },
        prompt: {
          type: 'string',
          description: 'Text prompt describing how to extend the video (what should happen next)',
        },
        model_name: {
          type: 'string',
          enum: ['kling-v1', 'kling-v1.5', 'kling-v1.6', 'kling-v2-master'],
          description: 'Model version to use for extension (default: kling-v2-master)',
        },
        duration: {
          type: 'string',
          enum: ['5'],
          description: 'Extension duration (fixed at 5 seconds)',
        },
        mode: {
          type: 'string',
          enum: ['standard', 'professional'],
          description: 'Video generation mode (default: standard)',
        },
      },
      required: ['task_id', 'prompt'],
    },
  },