This server provides AI image generation and editing capabilities via MCP, including text-to-image, image-to-image, multi-image fusion, sequential generation, and image browsing.
Text-to-image: Generate images from text prompts with configurable size, watermark, output format, and prompt optimization.
Image-to-image: Edit or transform existing images based on text instructions (style transfer, element removal, background change, etc.).
Multi-image fusion: Combine 2–14 reference images with a text prompt to create new fused images (e.g., outfit composition, person-with-scenery).
Sequential generation: Produce a set of related images (comic panels, brand visuals) from text and optional reference images.
Image browsing: Browse, filter, and retrieve local image files for use as references or to view generated content.
Model flexibility: Supports multiple Seedream models (5.0 Pro, 5.0/5.0 Lite, 4.5, 4.0) with differing capabilities (web search, streaming, layer decomposition, transparent background, etc.).
Web console: Optional browser-based interface for using image generation without an MCP client.
Style presets & prompt optimization: Built-in templates (anime, realistic, watercolor, oil painting) and standard/fast prompt enhancement modes.
Agent skills & resources: Exposes MCP resources for server info, model capabilities, and a downloadable skill pack for AI clients.
Uses .env files for configuration management, storing API keys and other environment variables for the Seedream 4.0 integration
Automatically generates Markdown reference formats for locally saved images, enabling easy embedding of generated images in Markdown documents
Built as a Python-based MCP server providing programmatic access to Seedream 4.0 image generation capabilities through Python APIs
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Seedream 4.0 MCP generate a serene mountain landscape at sunset with a lake reflection"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Related MCP server: Seedream 4.0 MCP Server
安装 uv，安装后即可直接使用 uvx 命令：
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"在火山引擎控制台获取 API 密钥，通过环境变量 ARK_API_KEY 提供。
# 通过环境变量提供密钥（推荐）
ARK_API_KEY=your_api_key_here uvx seedream-image-mcp
# 也可显式指定模型、尺寸等运行参数
ARK_API_KEY=your_api_key_here uvx seedream-image-mcp --model doubao-seedream-5.0 --default-size 2Kuvx 自动从 PyPI 拉取最新版本并在隔离环境运行——无需 clone 仓库、无需手动创建虚拟环境、无需安装依赖。
# 下载 docker-compose.yml
curl -O https://raw.githubusercontent.com/tengmmvp/Seedream_MCP/main/docker-compose.yml
# 可选：参照 .env.example 创建 .env 供 compose 只读挂载，免去下行命令的环境变量前置
# 未创建 .env 时 Docker 会自动建出同名目录充当挂载源导致挂载异常，请先 touch .env 或移除 compose 中的挂载行
# 启动服务
ARK_API_KEY=your_api_key_here SEEDREAM_HTTP_AUTH_TOKEN=your_token_here docker compose up -d服务以 streamable-http 传输监听容器内 8000 端口，MCP 端点路径为 /mcp；宿主机映射端口由 SEEDREAM_HTTP_PORT 控制，默认 8000。端口映射默认仅绑定回环地址 127.0.0.1，需从其他设备直连时，把 docker-compose.yml 改为 0.0.0.0:${SEEDREAM_HTTP_PORT:-8000}:8000 或指定宿主机网卡地址。映射一旦改为 0.0.0.0，服务即暴露给网络，SEEDREAM_HTTP_AUTH_TOKEN 会以明文 HTTP 在网络上传输；此时必须将服务置于 TLS 反向代理之后，或经 SEEDREAM_EXTRA_CLI_ARGS 向容器提供 TLS 证书参数，无 TLS 禁止对外暴露。
客户端接入配置以 Claude Desktop 为例，其他支持 streamable-http 的客户端同理：
{
"mcpServers": {
"seedream-image-mcp": {
"type": "http",
"url": "http://127.0.0.1:8000/mcp",
"headers": {
"Authorization": "Bearer <token>"
}
}
}
}<token> 为占位符，须与服务端环境变量 SEEDREAM_HTTP_AUTH_TOKEN 一致；若经 TLS 反向代理或容器内 TLS 暴露，url 改用 https:// 形态（如 https://mcp.example.com/mcp）。静态令牌鉴权不提供 OAuth 受保护资源元数据发现，标准 OAuth 客户端需手动配置凭据。
推荐通过
env注入ARK_API_KEY，避免把密钥写进args：命令行参数会出现在进程列表中，存在泄露风险。
编辑 claude_desktop_config.json：
{
"mcpServers": {
"seedream-image-mcp": {
"command": "uvx",
"args": ["seedream-image-mcp"],
"env": { "ARK_API_KEY": "your_api_key_here" }
}
}
}一条命令完成注册：
claude mcp add seedream-image-mcp --env ARK_API_KEY=your_api_key_here -- uvx seedream-image-mcp在项目根目录创建 .cursor/mcp.json：
{
"mcpServers": {
"seedream-image-mcp": {
"command": "uvx",
"args": ["seedream-image-mcp"],
"env": { "ARK_API_KEY": "your_api_key_here" }
}
}
}通用配置（command + args + env 字段同上）。Cline 编辑 cline_mcp_settings.json：
{
"mcpServers": {
"seedream-image-mcp": {
"command": "uvx",
"args": ["seedream-image-mcp"],
"env": { "ARK_API_KEY": "your_api_key_here" }
}
}
}需要指定模型/尺寸时，追加到
args，例如["seedream-image-mcp", "--model", "doubao-seedream-5.0"]。
配置后重启对应客户端即可使用。
不使用 MCP 客户端的用户也可以直接通过网页使用：以 --web 旗标（或环境变量 SEEDREAM_WEB_ENABLED=true）启动 streamable-http 传输后，浏览器访问 http://127.0.0.1:8000/web 即可打开操作台，覆盖文生图、图生图、多图融合、组图生成与历史图库。默认关闭，stdio 传输与未开启时不暴露任何 Web 端点。
ARK_API_KEY=your_api_key_here uvx seedream-image-mcp --transport streamable-http --web --auth-token your_token_here鉴权方式：网页本身无需令牌即可打开；网页的功能接口在部署配置了令牌时需要验证——在页面中输入后令牌仅存于当前标签页会话，关闭标签页即失效，下次使用需重新输入，不会出现在网址中。仅本机使用且未配置令牌时，全程无需输入任何东西，接口也只接受来自本页面与本机程序的请求。
根据文本提示词生成图像。该工具调用外部计费 API、在本地产出文件，非只读。
参数：
prompt (必需) - 图像生成的文本提示词，建议不超过 300 个汉字或 600 个英文单词
optimize_prompt_options (可选) - 提示词优化选项，支持 mode: "standard" 或 "fast"，fast 仅 5.0 Pro / 4.0 支持
size (可选) - 图像尺寸：1K、1.5K、2K、3K、4K 或 <宽>x<高> 像素值，默认使用配置文件值，需与所选模型兼容
watermark (可选) - 是否添加水印，默认使用配置文件值（默认 false）
response_format (可选) - 响应格式：url或b64_json，默认url
output_format (可选) - 输出文件格式，仅 5.0 系列（Pro/标准/Lite）支持 jpeg 或 png，默认不指定，由 API 按模型默认处理
stream (可选) - 是否启用流式输出，默认false（5.0 Pro 不支持）
tools (可选) - 模型工具配置，仅 doubao-seedream-5.0 / 5.0-lite 系列支持联网搜索，例如 [{"type":"web_search"}]
request_count (可选) - 同一提示并行发起的独立生成次数，每次各产出一张图，范围 1-10，默认 1
parallelism (可选) - 并行度上限，范围 1-10，默认 min(request_count, 10)，一般无需手动指定
auto_save (可选) - 是否自动保存到本地，默认使用全局配置（默认 true）
save_path (可选) - 自定义保存目录路径
custom_name (可选) - 自定义文件名前缀
调用示例：
{
"name": "text_to_image",
"arguments": {
"prompt": "水彩风格的江南水乡，清晨薄雾"
}
}根据输入图像和文本提示生成新图像。该工具调用外部计费 API、在本地产出文件，非只读。
参数：
prompt (可选) - 图像修改要求或风格转换指令，建议不超过 300 个汉字或 600 个英文单词；仅图层拆分场景可缺省，由模型自动识别拆分意图
optimize_prompt_options (可选) - 提示词优化选项，支持 mode: "standard" 或 "fast"，fast 仅 5.0 Pro / 4.0 支持
image (必需) - 输入图像，支持图像 URL、本地文件路径或 Base64 图片数据；本地文件路径须在读取范围内，其中相对路径仅限图片保存目录内
layer_decomposition (可选) - 是否开启图层拆分，仅 5.0 Pro 支持；开启后将单张输入图拆解为 1 张底图与最多 16 个带透明通道的 PNG 图层，图层条目额外返回 z_index、name、description、bounding_box 字段；output_format 仅控制底图格式，图层始终为 PNG
background (可选) - 透明通道，transparent 生成透明背景图（需输入单张带透明通道的图片，与 output_format=jpeg 互斥）或 opaque 生成常规图，仅 5.0 Pro 支持
size (可选) - 图像尺寸：1K、1.5K、2K、3K、4K 或 <宽>x<高> 像素值，默认使用配置文件值，需与所选模型兼容；图层拆分场景仅支持 1K、1.5K、2K 档位或 auto（按输入图自适应，未指定尺寸时的默认值）
watermark (可选) - 是否添加水印，默认使用配置文件值（默认 false）
response_format (可选) - 响应格式：url或b64_json，默认url
output_format (可选) - 输出文件格式，仅 5.0 系列（Pro/标准/Lite）支持 jpeg 或 png，默认不指定，由 API 按模型默认处理
stream (可选) - 是否启用流式输出，默认false（5.0 Pro 不支持）
tools (可选) - 模型工具配置，仅 doubao-seedream-5.0 / 5.0-lite 系列支持联网搜索，例如 [{"type":"web_search"}]
request_count (可选) - 同一提示并行发起的独立生成次数，每次各产出一张图，范围 1-10，默认 1
parallelism (可选) - 并行度上限，范围 1-10，默认 min(request_count, 10)，一般无需手动指定
auto_save (可选) - 是否自动保存到本地，默认使用全局配置（默认 true）
save_path (可选) - 自定义保存目录路径
custom_name (可选) - 自定义文件名前缀
调用示例：
{
"name": "image_to_image",
"arguments": {
"prompt": "把这张人像照片转换为吉卜力动画风格",
"image": "2026-08-15/image_to_image/portrait.jpeg"
}
}将多张图像融合生成新图像。该工具调用外部计费 API、在本地产出文件，非只读。
参数：
prompt (必需) - 图像融合要求或风格指令，建议不超过 300 个汉字或 600 个英文单词
optimize_prompt_options (可选) - 提示词优化选项，支持 mode: "standard" 或 "fast"，fast 仅 5.0 Pro / 4.0 支持
image (必需) - 输入图像（2-14 张；5.0 Pro 最多 10 张），每张支持图像 URL、本地文件路径或 Base64 图片数据；本地文件路径须在读取范围内，其中相对路径仅限图片保存目录内
size (可选) - 图像尺寸：1K、1.5K、2K、3K、4K 或 <宽>x<高> 像素值，默认使用配置文件值，需与所选模型兼容
watermark (可选) - 是否添加水印，默认使用配置文件值（默认 false）
response_format (可选) - 响应格式：url或b64_json，默认url
output_format (可选) - 输出文件格式，仅 5.0 系列（Pro/标准/Lite）支持 jpeg 或 png，默认不指定，由 API 按模型默认处理
stream (可选) - 是否启用流式输出，默认false（5.0 Pro 不支持）
tools (可选) - 模型工具配置，仅 doubao-seedream-5.0 / 5.0-lite 系列支持联网搜索，例如 [{"type":"web_search"}]
request_count (可选) - 同一提示并行发起的独立生成次数，每次各产出一张图，范围 1-10，默认 1
parallelism (可选) - 并行度上限，范围 1-10，默认 min(request_count, 10)，一般无需手动指定
auto_save (可选) - 是否自动保存到本地，默认使用全局配置（默认 true）
save_path (可选) - 自定义保存目录路径
custom_name (可选) - 自定义文件名前缀
调用示例：
{
"name": "multi_image_fusion",
"arguments": {
"prompt": "把两张人像融合为一张双人合影，影棚灯光",
"image": [
"2026-08-15/multi_image_fusion/person_a.jpeg",
"2026-08-15/multi_image_fusion/person_b.jpeg"
]
}
}连续生成多张图像，支持文生组图、单图生组图、多图生组图（仅 doubao-seedream-5.0 系列（5.0/5.0-lite）/4.5/4.0 支持；5.0 Pro 不支持组图）。该工具调用外部计费 API、在本地产出文件，非只读。
参数：
prompt (必需) - 图像生成的文本提示词，应明确指明生成数量和内容，建议不超过 300 个汉字或 600 个英文单词
optimize_prompt_options (可选) - 提示词优化选项，支持 mode: "standard" 或 "fast"，fast 仅 5.0 Pro / 4.0 支持
image (可选) - 参考图像（最多 14 张，且参考图数量与 max_images 之和不超过 15），每张支持图像 URL、本地文件路径或 Base64 图片数据；本地文件路径须在读取范围内，其中相对路径仅限图片保存目录内
size (可选) - 图像尺寸：1K、1.5K、2K、3K、4K 或 <宽>x<高> 像素值，默认使用配置文件值，需与所选模型兼容
watermark (可选) - 是否添加水印，默认使用配置文件值（默认 false）
max_images (可选) - 最大生成图像数量，范围 1-15，默认 15；提供参考图时默认自动扣减为 15 减参考图数量
response_format (可选) - 响应格式：url或b64_json，默认url
output_format (可选) - 输出文件格式，仅 5.0 系列（Pro/标准/Lite）支持 jpeg 或 png，默认不指定，由 API 按模型默认处理
stream (可选) - 是否启用流式输出，默认false
tools (可选) - 模型工具配置，仅 doubao-seedream-5.0 / 5.0-lite 系列支持联网搜索，例如 [{"type":"web_search"}]
request_count (可选) - 同一提示并行发起的独立生成次数，每次各产出一组图片，组内图片数量由模型按提示词决定，最多 max_images 张，范围 1-10，默认 1
parallelism (可选) - 并行度上限，范围 1-10，默认 min(request_count, 10)，一般无需手动指定
auto_save (可选) - 是否自动保存到本地，默认使用全局配置（默认 true）
save_path (可选) - 自定义保存目录路径
custom_name (可选) - 自定义文件名前缀
调用示例：
{
"name": "sequential_generation",
"arguments": {
"prompt": "四格漫画：一只柴犬的一天，起床、吃饭、散步、睡觉"
}
}浏览工作区中的图片文件，获取文件路径用于图像生成。该工具只读、幂等、不访问网络。
参数：
directory (可选) - 要浏览的目录路径，默认浏览图片保存目录；相对路径仅限图片保存目录内，绝对路径须在读取范围内。返回的条目为绝对路径，可直接作为参考图路径
recursive (可选) - 是否递归搜索子目录，默认true
max_depth (可选) - 最大搜索深度，范围 1-10，默认 3
limit (可选) - 返回的最大文件数量，范围 1-200，默认 50
offset (可选) - 分页偏移量（0-100000，从第几张开始返回），配合 limit 翻页，默认 0
format_filter (可选) - 过滤特定图片格式，如['.jpeg', '.png']
show_details (可选) - 是否显示详细文件信息，默认false
调用示例：
{
"name": "browse_images",
"arguments": {}
}各模型支持的能力与参数范围不同，选择模型时请留意：
提示：默认模型为 doubao-seedream-5.0（与 5.0 Lite 等价），开箱即用全部能力。切换到
doubao-seedream-5.0-pro后，组图、联网搜索、流式输出不可用，尺寸仅支持1K/1.5K/2K，默认档位2K，多图生图参考图上限降为 10 张，另独享图层拆分与透明背景能力。
各模型按张计费，单价如下：
计费说明：因审核等原因未成功输出的图片不计费；组图按实际生成的图片数量计费；5.0 Pro 图层拆分按每个图层实际像素档位单独计费，像素档以 261 万像素（约 1.5K）划界。本文价格为参考刊例，完整计费逻辑与最新单价以 火山方舟模型服务计费说明 为准。
除工具外，服务端还暴露以下 MCP 资源供客户端读取运行时信息：
服务器随包分发 Agent Skills 开放标准技能目录，为 AI 客户端提供图像生成的完整方法论，两种方式可用：
资源自动发现：客户端直接读取上表 skill:// 资源，主文件常驻资源列表，参考文件按需读取
手动安装：将包内 seedream_mcp/skills/seedream-image-generation/ 整目录拷贝到客户端技能目录，例如 Claude Code 的 ~/.claude/skills/
python -c "import pathlib, shutil, seedream_mcp; src = pathlib.Path(seedream_mcp.__file__).parent / 'skills' / 'seedream-image-generation'; shutil.copytree(src, pathlib.Path.home() / '.claude' / 'skills' / 'seedream-image-generation', dirs_exist_ok=True)"技能目录包含以下文件：
服务端内置以下 MCP 提示词模板，一键生成指定风格的文生图 prompt，可通过 subject 参数指定画面主题：
# 配置来源
--config-file TEXT # .env 配置文件路径；指定后不再读取项目根与当前目录的 .env
# 必需配置
--api-key TEXT # API 密钥（推荐用环境变量 ARK_API_KEY；命令行传入会留在进程列表与 shell 历史中）
# 模型与端点
--model [doubao-seedream-5.0-pro|doubao-seedream-5.0|doubao-seedream-5.0-lite|doubao-seedream-4.5|doubao-seedream-4.0]
# 模型选择；完整 Model ID 或 Endpoint ID 经 SEEDREAM_MODEL_ID 传入 (默认: doubao-seedream-5.0)
--default-size [1K|1.5K|2K|3K|4K|<宽>x<高>] # 默认生成尺寸，需与所选模型兼容 (默认: 2K)
--watermark # 启用水印
--no-watermark # 关闭水印
--base-url TEXT # 模型 API 端点 URL（须 https，http 需设 SEEDREAM_ALLOW_HTTP_BASE_URL=true 豁免）
# 日志
--log-level [DEBUG|INFO|WARNING|ERROR|CRITICAL] # 日志级别 (默认: INFO)
# 传输与 Web
--transport [stdio|streamable-http] # MCP 传输方式 (默认: stdio)
--host TEXT # streamable-http 监听地址 (默认: 127.0.0.1；绑定非回环地址必须配置鉴权令牌与 TLS，否则拒绝启动)
--port INTEGER # streamable-http 监听端口 (默认: 8000，范围 1-65535)
--auth-token TEXT # Bearer 鉴权令牌 (非回环绑定必须配置；推荐用 SEEDREAM_HTTP_AUTH_TOKEN)
--ssl-certfile TEXT # TLS 证书文件 (非回环绑定必须配置，与 --ssl-keyfile 成对)
--ssl-keyfile TEXT # TLS 私钥文件 (与 --ssl-certfile 成对)
--insecure-allow-non-tls # 允许非回环明文运行 (仅受信反向代理终结 TLS 场景)
--stateless # 无状态模式，仅影响带握手会话的旧规范修订客户端，代价是失去反向通道 (默认关闭)
--web # 开启 Web 操作台，浏览器访问 /web 直接使用 (默认关闭；未传入时按 SEEDREAM_WEB_ENABLED 解析)
--no-web # 关闭 Web 操作台，覆盖 SEEDREAM_WEB_ENABLED 的开启设置
--version # 打印版本号并退出安全提示：
localhost不被视为回环地址，须按非回环地址要求配置 Bearer 鉴权令牌与 TLS，未配置则拒绝启动；如需免鉴权使用回环地址，请改绑127.0.0.1或::1。非回环绑定默认按该地址校验 Host 与 Origin 头以防 DNS rebinding；通配绑定（0.0.0.0/::）无法预知访问地址，校验默认关闭，需配置SEEDREAM_HTTP_ALLOWED_HOSTS启用。跨源浏览器客户端接入/mcp（如网页版客户端）另需配置SEEDREAM_HTTP_ALLOWED_ORIGINS，配置后自动应答跨源预检并放行列表内来源；放行列表内的公网页面同时豁免浏览器的专用网络访问限制，可直接访问本地绑定的服务。生产与容器部署的密钥应经环境变量（ARK_API_KEY/SEEDREAM_HTTP_AUTH_TOKEN）传递，而非 CLI--api-key/--auth-token——命令行参数会留在进程列表与 shell 历史记录中；多用户主机上 streamable-http 即使绑定回环地址，也建议配置鉴权令牌。Web 操作台不改变上述传输层安全要求：开启后新增的 API 面全部强制令牌，免鉴权的仅限无数据的静态页面骨架。
# 基础使用
ARK_API_KEY=your_key uvx seedream-image-mcp
# 使用自定义配置文件
ARK_API_KEY=your_key uvx seedream-image-mcp --config-file ./my-config.env
# 切换其他模型（如 4.0 / 4.5）并指定尺寸与调试模式
ARK_API_KEY=your_key uvx seedream-image-mcp --model doubao-seedream-4.5 --default-size 4K --log-level DEBUG
# 高精度生图（5.0 Pro；注意：不支持组图 / 联网搜索 / 流式输出，尺寸仅 1K/1.5K/2K）
ARK_API_KEY=your_key uvx seedream-image-mcp --model doubao-seedream-5.0-pro全部配置项、默认值与说明见 .env.example，复制为 .env 后按需修改。
配置优先级：MCP 客户端显式配置（命令行参数） > 运行时系统环境变量 > .env 文件 > 默认值。
.env 加载规则：
使用 --config-file 时：仅加载指定文件。
未指定 --config-file 时：按“项目根 .env -> 当前工作目录 .env”顺序合并，后者覆盖前者。
.env 的值不会注入进程环境变量，仅按上述优先级解析后写入配置对象，避免污染全局状态；系统环境变量优先于 .env 文件。
保存目录由服务管理：按天清理与总量配额只作用于图片目录 <数据根目录>/.seedream/images，目录内所有过期的图片文件与空目录都会被删除，不看文件来源；经 save_path 保存到其他目录的文件不受管理。
多客户端部署建议显式设置 SEEDREAM_DATA_ROOT：数据根目录默认跟随客户端声明的 MCP Roots 变化，不同客户端的图片会散落在各自目录；显式声明后所有会话共用同一落点，读取范围与数据位置随之确定。
有状态会话依赖客户端正确断开：旧版协议客户端的 streamable-http 会话在客户端发送 DELETE 或进程退出时回收，客户端异常退出时会话驻留；大量短连客户端的部署建议改用 --stateless，新版协议客户端无会话、不受此影响。
Linux 宿主挂载目录属主：容器以 uid 1000 运行，compose 挂载的 ./.seedream 目录需对该用户可写：mkdir -p .seedream && chown 1000:1000 .seedream；Docker Desktop 不受影响。
出站连接不走系统代理：API 调用与图片下载固定忽略 HTTP_PROXY 等系统代理环境变量；企业代理环境需保证主机直连公网，或经网络层透明代理转发。
Q: uvx 命令不存在？
curl -LsSf https://astral.sh/uv/install.sh | shQ: 如何获取 API 密钥？ 访问 火山引擎控制台 创建密钥
Q: Docker 服务无法启动？ 确保设置了环境变量：
# Linux/macOS
export ARK_API_KEY=your_key
export SEEDREAM_HTTP_AUTH_TOKEN=your_token
docker compose up -d
# Windows
$env:ARK_API_KEY="your_key"
$env:SEEDREAM_HTTP_AUTH_TOKEN="your_token"
docker compose up -d# 克隆仓库
git clone https://github.com/tengmmvp/Seedream_MCP
cd Seedream_MCP
# 安装依赖（开发模式）
uv sync
# 创建 .env 文件
cp .env.example .env
# 编辑 .env 文件，添加您的 API 密钥
# 启动服务
uv run python -m seedream_mcp.server
# 或直接使用 API 密钥启动
uv run python -m seedream_mcp.server --api-key your_key@tengmmvp - 项目维护者
这个项目基于 MIT 许可证开源。更多信息请查看 LICENSE 文件。
本地图片浏览：
浏览工作目录中的图片文件，便于用户选择参考图或查看已生成内容。
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, destructiveHint, and idempotentHint, establishing safe read-only behavior. Description adds browsing context but no additional behavioral traits beyond what annotations convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is highly concise and front-loaded, communicating the core purpose immediately. No wasted words or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the six parameters and no output schema, the description lacks details on what browsing returns (e.g., file list format) or how pagination works. While annotations cover safety, the description is minimal for full contextual completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover all parameters with detailed explanations (e.g., directory, recursive, format_filter). Tool description does not add parameter meaning, but schema coverage is high, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states '浏览本地图片' (browse local images) in the working directory with specific use cases (selecting reference images or viewing generated content). It effectively distinguishes from sibling generation tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage context is implied (for selecting references or viewing outputs), but no explicit guidance on when to use vs. alternatives or when to avoid. Siblings are different in nature, so confusion is unlikely, but still lacks explicit direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
图文生图：
基于已有图片，结合文字指令进行图像编辑，包括图像元素增删、风格转化、材质替换、色调迁移、改变背景/视角/尺寸等。
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates the tool modifies images (readOnlyHint false), but it does not elaborate on behavioral traits such as whether the original image is altered (likely a new image is generated), authentication needs, or rate limits. The description adds minimal context beyond what the annotations already imply.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently conveys the tool's purpose and capabilities. It is front-loaded with the core function and avoids fluff, though it could benefit from a slightly more structured format.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (many parameters, no output schema), the description covers the essential purpose but lacks details on output format, behavior for optional parameters, and how it fits with sibling tools. It is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With schema description coverage at 0%, the description must compensate for parameter meaning, but it only mentions 'text instructions' and 'existing image' without detailing the required prompt and image parameters. Other parameters like size, watermark, etc., are not referenced, leaving the agent without guidance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it performs image-to-image editing based on an existing image and text instructions. It lists specific editing capabilities (style conversion, material replacement, etc.) and implicitly differentiates from siblings like text-to-image by specifying that it works on an existing image.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies it should be used when editing an existing image with text instructions, but it does not explicitly provide when to use or when not to use this tool versus alternatives like seedream_text_to_image or seedream_multi_image_fusion. No direct comparison or exclusion criteria are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
多图融合：
根据输入的文本描述和多张参考图片，融合它们的风格、元素等特征来生成新图像。如衣裤鞋帽与模特图融合成穿搭图，人物与风景融合为人物风景图等。
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates the tool generates new images, consistent with annotations (readOnlyHint=false, destructiveHint=false). However, it does not elaborate on side effects, memory usage, or behavior under specific conditions like failed inputs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with an example, conveying essential information without waste. It could be slightly more structured but is well-suited for quick comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains the core functionality but omits output details (e.g., format) and prerequisites. The rich schema compensates partially, but without an output schema, more contextual guidance would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description adds no parameter-specific details beyond the schema, but the nested schema provides comprehensive descriptions for each field. The description's lack of parameter info is acceptable as the schema already covers semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'multi-image fusion' and provides specific examples like merging clothing with models or people with landscapes, making the tool's purpose unmistakable and distinguishing it from siblings like text-to-image or image-to-image.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives examples of when to use (e.g., outfit creation, portrait with scenery) but does not explicitly state when not to use or offer direct comparisons to sibling tools, leaving the agent to infer usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
组图输出：
支持通过一张或者多张图片和文字信息，生成漫画分镜、品牌视觉等一组内容关联的图片。
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates image generation but does not disclose additional behavioral traits beyond annotations (readOnlyHint=false, destructiveHint=false). No mention of auth, rate limits, model-specific constraints, or output format. Schema provides some parameter details but description lacks behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence (27 characters) that immediately states the core purpose and examples. No superfluous text; it is optimally concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (many parameters, no output schema, minimal annotations), the description is adequate but leaves out important context like the sequential nature, response format, and model-specific limitations. Schema compensates partially, but overall completeness is average.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool description does not explain any parameters; the input schema has full descriptions for each parameter (high coverage). Thus the description adds no value beyond what's already in the schema, justifying the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a set of related images (group image output) from text and optional images, with examples like comic panels and brand visuals. It distinctly differs from sibling tools (seedream_browse_images, seedream_image_to_image, etc.) by focusing on sequential generation of multiple related images.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for generating groups of related images but does not explicitly state when to use it over alternatives or provide any exclusion criteria. No guidance on prerequisites or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
文生图：
通过给模型提供清晰准确的文字指令，即可快速获得符合描述的高质量单张图片。
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are minimal (readOnlyHint false, etc.). Description adds only 'quickly obtain' and 'high-quality', lacking behavioral details like cost, rate limits, or side effects. The agent may not know if generation is expensive or time-consuming.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words, front-loaded with core purpose. Could be more detailed without sacrificing conciseness, but it is efficiently structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having many parameters and sibling tools, the description is too brief. It lacks output details, parameter constraints, and usage context, making it insufficient for complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% – description does not explain any parameters. The schema itself has descriptions for each property, but the description fails to compensate for the low coverage, offering no added meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (文生图 = text-to-image) and resource (single high-quality image from text). It distinguishes from sibling tools like image_to_image or multi_image_fusion by emphasizing text input and single image output.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Does not mention when not to use it or provide context for selecting between siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.2.6seedream_browse_images1 field changedOutput schema / (root)Previous value: -{
- "$defs": {
- "Annotations": {
- "additionalProperties": true,
- "properties": {
- "audience": {
- "anyOf": [
- {
- "items": {
- "enum": [
- "user",
- "assistant"
- ],
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Audience"
- },
- "priority": {
- "anyOf": [
- {
- "maximum": 1,
- "minimum": 0,
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Priority"
- }
- },
- "title": "Annotations",
- "type": "object"
- },
- "TextContent": {
- "additionalProperties": true,
- "description": "Text content for a message.",
- "properties": {
- "_meta": {
- "anyOf": [
- {
- "additionalProperties": true,
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Meta"
- },
- "annotations": {
- "anyOf": [
- {
- "$ref": "#/$defs/Annotations"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "text": {
- "title": "Text",
- "type": "string"
- },
- "type": {
- "const": "text",
- "title": "Type",
- "type": "string"
- }
- },
- "required": [
- "type",
- "text"
- ],
- "title": "TextContent",
- "type": "object"
- }
- },
- "properties": {
- "result": {
- "items": {
- "$ref": "#/$defs/TextContent"
- },
- "title": "Result",
- "type": "array"
- }
- },
- "required": [
- "result"
- ],
- "title": "seedream_browse_imagesOutput",
- "type": "object"
-}New value: +nullseedream_image_to_image12 fields changedInput schema / $defs / GenerationToolAdded value: +{
+ "additionalProperties": false,
+ "description": "模型工具配置。",
+ "properties": {
+ "type": {
+ "$ref": "#/$defs/GenerationToolType",
+ "description": "工具类型，目前仅支持 web_search。"
+ }
+ },
+ "required": [
+ "type"
+ ],
+ "title": "GenerationTool",
+ "type": "object"
+}Input schema / $defs / GenerationToolTypeAdded value: +{
+ "description": "模型工具类型枚举",
+ "enum": [
+ "web_search"
+ ],
+ "title": "GenerationToolType",
+ "type": "string"
+}Input schema / $defs / ImageToImageInput / properties / image / descriptionPrevious value: -"待转换的图片，支持 URL、本地文件路径。"New value: +"参考图片，支持 URL、本地文件路径。"Input schema / $defs / ImageToImageInput / properties / output_formatAdded value: +{
+ "anyOf": [
+ {
+ "$ref": "#/$defs/OutputFormat"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "输出图片格式，仅 doubao-seedream-5.0 支持 jpeg 或 png。"
+}Input schema / $defs / ImageToImageInput / properties / parallelismAdded value: +{
+ "anyOf": [
+ {
+ "maximum": 4,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "并行度上限；未提供时自动使用 min(request_count, 4)。",
+ "title": "Parallelism"
+}Input schema / $defs / ImageToImageInput / properties / request_countAdded value: +{
+ "default": 1,
+ "description": "并行请求次数，1 表示单次请求；可用于一次发起多次生成以减少等待。",
+ "maximum": 4,
+ "minimum": 1,
+ "title": "Request Count",
+ "type": "integer"
+}Input schema / $defs / ImageToImageInput / properties / size / descriptionPrevious value: -"生成图片尺寸，可选 1K/2K/4K；未提供时使用全局默认值。"New value: +"生成图片尺寸，可选 1K/2K/3K/4K 或 <宽>x<高> 像素值；未提供时使用全局默认值。"Input schema / $defs / ImageToImageInput / properties / toolsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "$ref": "#/$defs/GenerationTool"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "模型工具配置，仅 doubao-seedream-5.0 支持，目前仅支持 web_search。",
+ "title": "Tools"
+}Input schema / $defs / OptimizePromptOptions / descriptionPrevious value: -"提示词优化配置模型。\n\n配置提示词优化策略，平衡生成质量与响应速度。"New value: +"提示词优化配置模型\n\n配置提示词优化策略，平衡生成质量与响应速度。"Input schema / $defs / OutputFormatAdded value: +{
+ "description": "图片文件输出格式枚举",
+ "enum": [
+ "jpeg",
+ "png"
+ ],
+ "title": "OutputFormat",
+ "type": "string"
+}Input schema / $defs / ResponseFormat / descriptionPrevious value: -"图片生成响应格式枚举。\n\n定义生成结果的返回格式，支持 URL 链接和 Base64 编码两种方式。"New value: +"图片生成响应格式枚举"Output schema / (root)Previous value: -{
- "$defs": {
- "Annotations": {
- "additionalProperties": true,
- "properties": {
- "audience": {
- "anyOf": [
- {
- "items": {
- "enum": [
- "user",
- "assistant"
- ],
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Audience"
- },
- "priority": {
- "anyOf": [
- {
- "maximum": 1,
- "minimum": 0,
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Priority"
- }
- },
- "title": "Annotations",
- "type": "object"
- },
- "TextContent": {
- "additionalProperties": true,
- "description": "Text content for a message.",
- "properties": {
- "_meta": {
- "anyOf": [
- {
- "additionalProperties": true,
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Meta"
- },
- "annotations": {
- "anyOf": [
- {
- "$ref": "#/$defs/Annotations"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "text": {
- "title": "Text",
- "type": "string"
- },
- "type": {
- "const": "text",
- "title": "Type",
- "type": "string"
- }
- },
- "required": [
- "type",
- "text"
- ],
- "title": "TextContent",
- "type": "object"
- }
- },
- "properties": {
- "result": {
- "items": {
- "$ref": "#/$defs/TextContent"
- },
- "title": "Result",
- "type": "array"
- }
- },
- "required": [
- "result"
- ],
- "title": "seedream_image_to_imageOutput",
- "type": "object"
-}New value: +nullseedream_multi_image_fusion13 fields changedInput schema / $defs / GenerationToolAdded value: +{
+ "additionalProperties": false,
+ "description": "模型工具配置。",
+ "properties": {
+ "type": {
+ "$ref": "#/$defs/GenerationToolType",
+ "description": "工具类型，目前仅支持 web_search。"
+ }
+ },
+ "required": [
+ "type"
+ ],
+ "title": "GenerationTool",
+ "type": "object"
+}Input schema / $defs / GenerationToolTypeAdded value: +{
+ "description": "模型工具类型枚举",
+ "enum": [
+ "web_search"
+ ],
+ "title": "GenerationToolType",
+ "type": "string"
+}Input schema / $defs / MultiImageFusionInput / properties / image / descriptionPrevious value: -"参与融合的图片列表，支持 URL、本地路径，数量2-5张。"New value: +"图片列表，支持 URL、本地路径，数量2-14张。"Input schema / $defs / MultiImageFusionInput / properties / image / maxItemsPrevious value: -5New value: +14Input schema / $defs / MultiImageFusionInput / properties / output_formatAdded value: +{
+ "anyOf": [
+ {
+ "$ref": "#/$defs/OutputFormat"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "输出图片格式，仅 doubao-seedream-5.0 支持 jpeg 或 png。"
+}Input schema / $defs / MultiImageFusionInput / properties / parallelismAdded value: +{
+ "anyOf": [
+ {
+ "maximum": 4,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "并行度上限；未提供时自动使用 min(request_count, 4)。",
+ "title": "Parallelism"
+}Input schema / $defs / MultiImageFusionInput / properties / request_countAdded value: +{
+ "default": 1,
+ "description": "并行请求次数，1 表示单次请求；可用于一次发起多次生成以减少等待。",
+ "maximum": 4,
+ "minimum": 1,
+ "title": "Request Count",
+ "type": "integer"
+}Input schema / $defs / MultiImageFusionInput / properties / size / descriptionPrevious value: -"生成图片尺寸，可选 1K/2K/4K；未提供时使用全局默认值。"New value: +"生成图片尺寸，可选 1K/2K/3K/4K 或 <宽>x<高> 像素值；未提供时使用全局默认值。"Input schema / $defs / MultiImageFusionInput / properties / toolsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "$ref": "#/$defs/GenerationTool"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "模型工具配置，仅 doubao-seedream-5.0 支持，目前仅支持 web_search。",
+ "title": "Tools"
+}Input schema / $defs / OptimizePromptOptions / descriptionPrevious value: -"提示词优化配置模型。\n\n配置提示词优化策略，平衡生成质量与响应速度。"New value: +"提示词优化配置模型\n\n配置提示词优化策略，平衡生成质量与响应速度。"Input schema / $defs / OutputFormatAdded value: +{
+ "description": "图片文件输出格式枚举",
+ "enum": [
+ "jpeg",
+ "png"
+ ],
+ "title": "OutputFormat",
+ "type": "string"
+}Input schema / $defs / ResponseFormat / descriptionPrevious value: -"图片生成响应格式枚举。\n\n定义生成结果的返回格式，支持 URL 链接和 Base64 编码两种方式。"New value: +"图片生成响应格式枚举"Output schema / (root)Previous value: -{
- "$defs": {
- "Annotations": {
- "additionalProperties": true,
- "properties": {
- "audience": {
- "anyOf": [
- {
- "items": {
- "enum": [
- "user",
- "assistant"
- ],
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Audience"
- },
- "priority": {
- "anyOf": [
- {
- "maximum": 1,
- "minimum": 0,
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Priority"
- }
- },
- "title": "Annotations",
- "type": "object"
- },
- "TextContent": {
- "additionalProperties": true,
- "description": "Text content for a message.",
- "properties": {
- "_meta": {
- "anyOf": [
- {
- "additionalProperties": true,
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Meta"
- },
- "annotations": {
- "anyOf": [
- {
- "$ref": "#/$defs/Annotations"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "text": {
- "title": "Text",
- "type": "string"
- },
- "type": {
- "const": "text",
- "title": "Type",
- "type": "string"
- }
- },
- "required": [
- "type",
- "text"
- ],
- "title": "TextContent",
- "type": "object"
- }
- },
- "properties": {
- "result": {
- "items": {
- "$ref": "#/$defs/TextContent"
- },
- "title": "Result",
- "type": "array"
- }
- },
- "required": [
- "result"
- ],
- "title": "seedream_multi_image_fusionOutput",
- "type": "object"
-}New value: +nullseedream_sequential_generation14 fields changedInput schema / $defs / GenerationToolAdded value: +{
+ "additionalProperties": false,
+ "description": "模型工具配置。",
+ "properties": {
+ "type": {
+ "$ref": "#/$defs/GenerationToolType",
+ "description": "工具类型，目前仅支持 web_search。"
+ }
+ },
+ "required": [
+ "type"
+ ],
+ "title": "GenerationTool",
+ "type": "object"
+}Input schema / $defs / GenerationToolTypeAdded value: +{
+ "description": "模型工具类型枚举",
+ "enum": [
+ "web_search"
+ ],
+ "title": "GenerationToolType",
+ "type": "string"
+}Input schema / $defs / OptimizePromptOptions / descriptionPrevious value: -"提示词优化配置模型。\n\n配置提示词优化策略，平衡生成质量与响应速度。"New value: +"提示词优化配置模型\n\n配置提示词优化策略，平衡生成质量与响应速度。"Input schema / $defs / OutputFormatAdded value: +{
+ "description": "图片文件输出格式枚举",
+ "enum": [
+ "jpeg",
+ "png"
+ ],
+ "title": "OutputFormat",
+ "type": "string"
+}Input schema / $defs / ResponseFormat / descriptionPrevious value: -"图片生成响应格式枚举。\n\n定义生成结果的返回格式，支持 URL 链接和 Base64 编码两种方式。"New value: +"图片生成响应格式枚举"Input schema / $defs / SequentialGenerationInput / properties / image / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / $defs / SequentialGenerationInput / properties / image / descriptionPrevious value: -"可选的参考图片，支持单张或多张。"New value: +"可选的参考图片，支持 URL、本地路径，单张或多张，最多 14 张。"Input schema / $defs / SequentialGenerationInput / properties / max_images / defaultPrevious value: -4New value: +15Input schema / $defs / SequentialGenerationInput / properties / output_formatAdded value: +{
+ "anyOf": [
+ {
+ "$ref": "#/$defs/OutputFormat"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "输出图片格式，仅 doubao-seedream-5.0 支持 jpeg 或 png。"
+}Input schema / $defs / SequentialGenerationInput / properties / parallelismAdded value: +{
+ "anyOf": [
+ {
+ "maximum": 4,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "并行度上限；未提供时自动使用 min(request_count, 4)。",
+ "title": "Parallelism"
+}Input schema / $defs / SequentialGenerationInput / properties / request_countAdded value: +{
+ "default": 1,
+ "description": "并行请求次数，1 表示单次请求；可用于一次发起多次生成以减少等待。",
+ "maximum": 4,
+ "minimum": 1,
+ "title": "Request Count",
+ "type": "integer"
+}Input schema / $defs / SequentialGenerationInput / properties / size / descriptionPrevious value: -"生成图片尺寸，可选 1K/2K/4K；未提供时使用全局默认值。"New value: +"生成图片尺寸，可选 1K/2K/3K/4K 或 <宽>x<高> 像素值；未提供时使用全局默认值。"Input schema / $defs / SequentialGenerationInput / properties / toolsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "$ref": "#/$defs/GenerationTool"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "模型工具配置，仅 doubao-seedream-5.0 支持，目前仅支持 web_search。",
+ "title": "Tools"
+}Output schema / (root)Previous value: -{
- "$defs": {
- "Annotations": {
- "additionalProperties": true,
- "properties": {
- "audience": {
- "anyOf": [
- {
- "items": {
- "enum": [
- "user",
- "assistant"
- ],
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Audience"
- },
- "priority": {
- "anyOf": [
- {
- "maximum": 1,
- "minimum": 0,
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Priority"
- }
- },
- "title": "Annotations",
- "type": "object"
- },
- "TextContent": {
- "additionalProperties": true,
- "description": "Text content for a message.",
- "properties": {
- "_meta": {
- "anyOf": [
- {
- "additionalProperties": true,
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Meta"
- },
- "annotations": {
- "anyOf": [
- {
- "$ref": "#/$defs/Annotations"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "text": {
- "title": "Text",
- "type": "string"
- },
- "type": {
- "const": "text",
- "title": "Type",
- "type": "string"
- }
- },
- "required": [
- "type",
- "text"
- ],
- "title": "TextContent",
- "type": "object"
- }
- },
- "properties": {
- "result": {
- "items": {
- "$ref": "#/$defs/TextContent"
- },
- "title": "Result",
- "type": "array"
- }
- },
- "required": [
- "result"
- ],
- "title": "seedream_sequential_generationOutput",
- "type": "object"
-}New value: +nullseedream_text_to_image11 fields changedInput schema / $defs / GenerationToolAdded value: +{
+ "additionalProperties": false,
+ "description": "模型工具配置。",
+ "properties": {
+ "type": {
+ "$ref": "#/$defs/GenerationToolType",
+ "description": "工具类型，目前仅支持 web_search。"
+ }
+ },
+ "required": [
+ "type"
+ ],
+ "title": "GenerationTool",
+ "type": "object"
+}Input schema / $defs / GenerationToolTypeAdded value: +{
+ "description": "模型工具类型枚举",
+ "enum": [
+ "web_search"
+ ],
+ "title": "GenerationToolType",
+ "type": "string"
+}Input schema / $defs / OptimizePromptOptions / descriptionPrevious value: -"提示词优化配置模型。\n\n配置提示词优化策略，平衡生成质量与响应速度。"New value: +"提示词优化配置模型\n\n配置提示词优化策略，平衡生成质量与响应速度。"Input schema / $defs / OutputFormatAdded value: +{
+ "description": "图片文件输出格式枚举",
+ "enum": [
+ "jpeg",
+ "png"
+ ],
+ "title": "OutputFormat",
+ "type": "string"
+}Input schema / $defs / ResponseFormat / descriptionPrevious value: -"图片生成响应格式枚举。\n\n定义生成结果的返回格式，支持 URL 链接和 Base64 编码两种方式。"New value: +"图片生成响应格式枚举"Input schema / $defs / TextToImageInput / properties / output_formatAdded value: +{
+ "anyOf": [
+ {
+ "$ref": "#/$defs/OutputFormat"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "输出图片格式，仅 doubao-seedream-5.0 支持 jpeg 或 png。"
+}Input schema / $defs / TextToImageInput / properties / parallelismAdded value: +{
+ "anyOf": [
+ {
+ "maximum": 4,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "并行度上限；未提供时自动使用 min(request_count, 4)。",
+ "title": "Parallelism"
+}Input schema / $defs / TextToImageInput / properties / request_countAdded value: +{
+ "default": 1,
+ "description": "并行请求次数，1 表示单次请求；可用于一次发起多次生成以减少等待。",
+ "maximum": 4,
+ "minimum": 1,
+ "title": "Request Count",
+ "type": "integer"
+}Input schema / $defs / TextToImageInput / properties / size / descriptionPrevious value: -"生成图片尺寸，可选 1K/2K/4K；未提供时使用全局默认值。"New value: +"生成图片尺寸，可选 1K/2K/3K/4K 或 <宽>x<高> 像素值；未提供时使用全局默认值。"Input schema / $defs / TextToImageInput / properties / toolsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "$ref": "#/$defs/GenerationTool"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "模型工具配置，仅 doubao-seedream-5.0 支持，目前仅支持 web_search。",
+ "title": "Tools"
+}Output schema / (root)Previous value: -{
- "$defs": {
- "Annotations": {
- "additionalProperties": true,
- "properties": {
- "audience": {
- "anyOf": [
- {
- "items": {
- "enum": [
- "user",
- "assistant"
- ],
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Audience"
- },
- "priority": {
- "anyOf": [
- {
- "maximum": 1,
- "minimum": 0,
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Priority"
- }
- },
- "title": "Annotations",
- "type": "object"
- },
- "TextContent": {
- "additionalProperties": true,
- "description": "Text content for a message.",
- "properties": {
- "_meta": {
- "anyOf": [
- {
- "additionalProperties": true,
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "title": "Meta"
- },
- "annotations": {
- "anyOf": [
- {
- "$ref": "#/$defs/Annotations"
- },
- {
- "type": "null"
- }
- ],
- "default": null
- },
- "text": {
- "title": "Text",
- "type": "string"
- },
- "type": {
- "const": "text",
- "title": "Type",
- "type": "string"
- }
- },
- "required": [
- "type",
- "text"
- ],
- "title": "TextContent",
- "type": "object"
- }
- },
- "properties": {
- "result": {
- "items": {
- "$ref": "#/$defs/TextContent"
- },
- "title": "Result",
- "type": "array"
- }
- },
- "required": [
- "result"
- ],
- "title": "seedream_text_to_imageOutput",
- "type": "object"
-}New value: +nullseedream_browse_imagesseedream_image_to_imageseedream_multi_image_fusionseedream_sequential_generationseedream_text_to_imageScored across 5 tools
Each tool has a clearly distinct purpose: browsing, text-to-image, image editing, multi-image fusion, and sequential generation. No overlapping functionality.
All tools follow the consistent 'seedream_verb_noun' snake_case pattern (e.g., seedream_text_to_image). No mixing of conventions.
With 5 tools, the server is well-scoped for image generation tasks. Each tool covers a distinct operation without unnecessary bloat or gaps.
Core image generation workflows (text-to-image, editing, fusion, sequential) are covered. Minor gap: no tool for retrieving image metadata or management, but not essential for generation.
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Generate AI images and videos from any compatible MCP client.
Generate AI images, video, music, and sound effects, and upscale them, from any MCP client.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
