Seedream MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VOLC_MODEL | No | Model version, defaults to doubao-seedream-5-0-260128 | doubao-seedream-5-0-260128 |
| VOLC_API_KEY | Yes | Your Volcengine API Key |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| seedream_text_to_imageA | 文生图:根据文本描述生成图片。 使用 Seedream 模型(默认 5.0)根据文本提示词生成高质量图片。 支持 1K/2K/3K/4K 等多种分辨率,可一次生成多张图片。 示例:
注意:5.0 和 4.0 版本支持 n>1(多张),4.5 仅支持 n=1。 |
| seedream_image_to_imageB | 图生图:基于参考图片生成新图片。 提供一张参考图片 URL,结合文本描述生成新的图片。 支持 4.5 和 5.0 模型。 示例:
|
| seedream_merge_imagesA | 多图融合:融合多张图片生成新图片。 提供多张参考图片 URL,结合文本描述将它们融合成一张新图片。 最多支持 10 张图片,可在提示词中用「图1」「图2」等指代各图片。 示例:
|
| seedream_generate_sequenceA | 组图生成:根据文本描述生成一组连续图片。 适用于需要生成多张连续画面的场景,如故事板、漫画分镜等。 支持 4.5 和 5.0 模型,每批最多 15 张。 示例:
|
| seedream_web_search_generateA | 联网搜索 + 文生图:结合实时信息生成图片(仅 5.0 模型)。 Seedream 5.0 专属功能,在生图前先搜索互联网获取实时信息, 适合需要结合最新资讯、热点事件或特定知识生成图片的场景。 示例:
|
| seedream_list_modelsA | 列出可用的 Seedream 模型版本及其特性说明。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| seedream_expert | 成为 Seedream 图片生成专家,根据用户需求推荐合适的工具和参数 |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: sequence generation, image-to-image, model listing, image merging, text-to-image, and web search generation. No two tools overlap in functionality.
All tools follow a consistent 'seedream_verb_noun' pattern using snake_case, making them predictable and easy to distinguish.
With 6 tools, the server is well-scoped for image generation tasks, covering all major operations without being bloated or too sparse.
The tool set covers the full lifecycle of image generation: text-to-image, image-to-image, merging, sequence generation, and web-enhanced generation, plus model listing. No obvious gaps exist.