doubao-seedream-mcp

doubao-seedream-mcp

封装豆包 Seedream 图像生成模型为 MCP 服务,支持文生图、图生图、组图及联网搜索生图,部署在 Cloudflare Workers 上

Category
Visit Server

README

doubao-seedream-mcp

将豆包 Seedream 图片生成模型封装为 MCP 服务,部署在 Cloudflare Workers 上,开箱即用。

功能

支持豆包 Seedream API 的全部能力:

Tool 功能 适用模型
text_to_image 文生图 全部
image_to_image 图生图(单图/多图参考,最多14张) 全部
generate_image_group 生成组图(内容关联的多张图) 5.0-lite / 4.5 / 4.0
search_and_generate 联网搜索 + 生图 5.0-lite

通用参数支持:

  • 尺寸2K / 3K / 4K 或自定义像素值(如 2048x2048
  • 输出格式 — PNG / JPEG(仅 5.0-lite 支持切换)
  • 返回方式 — URL(24小时有效链接)或 Base64(直接展示)
  • 水印控制 — 开启/关闭右下角 "AI生成" 水印
  • 提示词优化 — standard(高质量)/ fast(快速)

快速使用

前置条件

  1. 一个火山方舟的 API Key
  2. 在火山方舟控制台开通 Seedream 模型的访问权限

MCP 客户端配置

在你的 MCP 客户端(Claude Desktop、Cursor、Kiro 等)中添加:

方式一:远程 URL(支持 Streamable HTTP 的客户端,如 Cursor、Kiro)

复制以下配置,替换 <your-ark-api-key> 为你的火山方舟 API Key 即可:

{
  "mcpServers": {
    "doubao-seedream": {
      "url": "https://seedream.mcp.996.ninja/mcp",
      "headers": {
        "Authorization": "Bearer <your-ark-api-key>",
        "X-Model": "doubao-seedream-5-0-260128"
      }
    }
  }
}

方式二:通过 mcp-remote 代理(Claude Desktop 等仅支持 stdio 的客户端)

{
  "mcpServers": {
    "doubao-seedream": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://seedream.mcp.996.ninja/mcp",
        "--header",
        "Authorization:Bearer <your-ark-api-key>",
        "--header",
        "X-Model:doubao-seedream-5-0-260128"
      ]
    }
  }
}

方式三:使用 VS Code / Cursor 的 MCP 配置(.vscode/mcp.json

在项目根目录创建 .vscode/mcp.json

{
  "servers": {
    "doubao-seedream": {
      "url": "https://seedream.mcp.996.ninja/mcp",
      "headers": {
        "Authorization": "Bearer <your-ark-api-key>",
        "X-Model": "doubao-seedream-5-0-260128"
      }
    }
  }
}

配置说明

Header 必填 说明
Authorization 火山方舟 API Key,格式 Bearer ark-xxx
X-Model 模型名称,默认 doubao-seedream-5-0-260128

支持的模型:

  • doubao-seedream-5-0-260128(推荐,功能最全)
  • doubao-seedream-4.5
  • doubao-seedream-4.0
  • doubao-seedream-3.0-t2i

自部署

如果你想部署自己的实例:

# 克隆项目
git clone <repo-url>
cd doubao-seedream-mcp

# 安装依赖
npm install

# 本地开发
npm run dev

# 部署到 Cloudflare Workers
npm run deploy

也可以通过环境变量设置默认的 API Key(这样用户无需在 header 中传递):

npx wrangler secret put ARK_API_KEY
npx wrangler secret put ARK_MODEL

本地测试

npm run dev

# 用 MCP Inspector 测试
npx @modelcontextprotocol/inspector@latest
# 在 Inspector 中输入 http://localhost:8787/mcp

使用示例

配置好 MCP 后,直接对 AI 说:

  • "帮我生成一张赛博朋克风格的城市夜景"
  • "参考这张图片,生成一张类似风格的日落场景" (附图)
  • "生成一组4格漫画,讲述一只猫咪的日常"
  • "搜索最新的 iPhone 设计,生成一张产品宣传图"

API 参考

基于火山方舟 Seedream API 文档

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured