Doubao Image/Video Generation MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DOUBAO_API_KEY | Yes | API 密钥 | |
| DOUBAO_IMAGE_ENDPOINT_ID | Yes | 图片生成推理接入点 ID | |
| DOUBAO_VIDEO_ENDPOINT_ID | Yes | 视频生成推理接入点 ID | |
| DOUBAO_DEFAULT_IMAGE_MODEL | No | 默认图片生成模型 | doubao-seedream-4-5 |
| DOUBAO_DEFAULT_VIDEO_MODEL | No | 默认视频生成模型 | doubao-seedance-1.0-lite-t2v |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | 使用豆包 Seedream 模型生成图片 支持功能:
参数说明:
重要提示: 如果遇到 InvalidEndpointOrModel.NotFound 错误,请在火山引擎控制台创建推理接入点,并使用 endpoint_id 参数 |
| generate_videoA | 使用豆包 Seedance 模型生成视频 支持功能:
参数说明:
返回: 任务 ID,需要使用 query_video_task 查询结果 |
| query_video_taskA | 查询豆包视频生成任务的状态和结果 视频生成是异步任务,需要使用此工具查询任务状态:
参数说明:
返回: 任务状态和结果 (成功时包含视频下载 URL) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three tools have clearly distinct purposes: generate_image handles image generation with various modes, generate_video handles video generation with its own modes, and query_video_task is a dedicated status checker for video tasks. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern in snake_case: generate_image, generate_video, query_video_task. The naming is predictable and uniform throughout the set.
Three tools is well-scoped for a server focused on image and video generation. It covers the core operations (generate images, generate videos, query video tasks) without being too sparse or bloated.
The server provides good coverage for its domain: image generation with multiple modes, video generation with multiple modes, and a query tool for async video tasks. A minor gap is the lack of a similar query tool for image tasks, but this is not critical as image generation appears to be synchronous.