Dreamshot MCP Server
Enables AI image and video generation using Dreamshot's API, supporting tools like image editing, video creation, and enhancement directly from MCP-compatible clients.
README
Dreamshot MCP Server
MCP server for Dreamshot AI image and video generation. Use it with Claude Desktop, Claude Code, or any MCP-compatible client.
Quick Start
1. Get your API key
Sign up at dreamshot.io and get your API key from Settings > API.
2. Add to your MCP config
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"dreamshot": {
"command": "npx",
"args": ["@dreamshot/mcp-server"],
"env": {
"DREAMSHOT_API_KEY": "dst_your_key_here"
}
}
}
}
Claude Code (.mcp.json):
{
"mcpServers": {
"dreamshot": {
"command": "npx",
"args": ["@dreamshot/mcp-server"],
"env": {
"DREAMSHOT_API_KEY": "dst_your_key_here"
}
}
}
}
3. Start using it
Ask Claude to generate images or videos:
"Generate a product photo on a marble surface" "Create a 5-second video panning around this product" "Upscale this image to 4K"
Available Tools
| Tool | Description |
|---|---|
dreamshot_list_tools |
List available tools with variants and credit costs |
dreamshot_generate |
Start an AI generation (returns generationId) |
dreamshot_status |
Check generation status (pending/completed/failed) |
dreamshot_media |
Get download URLs for completed generations |
dreamshot_credits |
Check remaining credits |
Supported AI Tools
Image Editing (ai_edit)
Edit images using AI with text prompts.
| Variant | Credits | Description |
|---|---|---|
ultra |
1 | Best quality, supports model references |
nano |
0.5 | Fast iterations |
seedream |
0.5 | Seedream model |
flux |
0.5 | FLUX-based editing |
flux2max |
1 | FLUX 2 Max quality |
gpt_image_1 |
1.5 | OpenAI GPT Image |
Video Generation (create_video)
Generate videos from images and/or text prompts.
| Model | Credits | Description |
|---|---|---|
google/veo-3.1 |
16+ | Latest Veo with audio |
kwaivgi/kling-v2.6 |
4-14 | Kling 2.6 Pro |
fal-ai/kling-v3-pro |
17 | Kling 3.0 Pro |
openai/sora-2 |
4-12 | OpenAI Sora 2 |
openai/sora-2-pro |
8-24 | OpenAI Sora 2 Pro |
Image Enhancement (enhancer)
Upscale and enhance image quality.
| Variant | Credits | Description |
|---|---|---|
dreamshot |
2 | General upscaling |
magnific_precision |
3 | Sharp, detailed |
magnific_creative |
4 | Creative enhancement |
More Tools
generate_image- Generate from trained modelscreate_anything- Text-to-image with FLUX
Run dreamshot_list_tools to see all available tools and current pricing.
Example Workflow
1. Check credits
→ dreamshot_credits()
2. Start generation
→ dreamshot_generate(
tool: "ai_edit",
variant: "ultra",
prompt: "luxury perfume on marble",
imageUrls: ["https://..."]
)
→ Returns: { generationId: "abc123" }
3. Poll status
→ dreamshot_status(generationId: "abc123")
→ Returns: { status: "pending" }
4. Poll again
→ dreamshot_status(generationId: "abc123")
→ Returns: { status: "completed", mediaItems: [...] }
5. Get download URLs
→ dreamshot_media(generationId: "abc123")
→ Returns: { media: [{ downloadUrl: "..." }] }
Environment Variables
| Variable | Required | Description |
|---|---|---|
DREAMSHOT_API_KEY |
Yes | Your Dreamshot API key (dst_xxx) |
DREAMSHOT_BASE_URL |
No | Custom API URL (defaults to https://app.dreamshot.io/api/v1) |
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build
npm run build
# Run built version
npm start
Links
- Dreamshot - AI photo generation platform
- API Documentation
- Get API Key
- MCP Specification
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。