广告合作
MCP.so
登录

Stability AI MCP Server

@tadasant

代码仓库

基本信息

分类

其他

许可证

MIT

传输方式

stdio

作者

tadasant

关于 Stability AI MCP Server

MCP Server integrating MCP Clients with Stability AI-powered image manipulation functionalities: generate, edit, upscale, and more.

Stability AI MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-server-stability-ai": {
      "command": "npx",
      "args": [
        "@smithery/cli",
        "install",
        "mcp-server-stability-ai",
        "--client",
        "claude"
      ]
    }
  }
}

Stability AI MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Stability AI MCP Server?

Stability AI MCP Server is an MCP (Model Context Protocol) server that integrates MCP clients like Claude Desktop with Stability AI's Stable Diffusion image manipulation APIs. It allows users to generate, edit, upscale, and manipulate images using tools powered by Stability AI's hosted REST API. Users need a Stability AI API key (free tier available) to get started.

How to use Stability AI MCP Server?

Install the server via npm or configure it in your MCP client (e.g., Claude Desktop) by setting the STABILITY_AI_API_KEY environment variable and optionally IMAGE_STORAGE_DIRECTORY. Invoke tools like generate-image, remove-background, or upscale-fast by describing the desired action in natural language through the client. All generated images are saved automatically to the configured local directory.

Key features of Stability AI MCP Server

  • Generate images from text prompts with sensible defaults
  • Remove backgrounds, outpainting, and search-and-replace objects
  • Upscale images by 4x or up to 4K quality
  • Translate sketches into production-grade images
  • Control image generation by style or structure references
  • Automatic metadata logging for request tracking

Use cases of Stability AI MCP Server

  • Quickly generate high-quality images for design or content creation
  • Edit product photos by removing backgrounds or replacing elements
  • Uncropping or extending images for social media or printing
  • Transform rough sketches into polished illustrations
  • Apply a consistent artistic style across multiple images

常见问题

1

What do I need to use this server?

You need a Stability AI API key (obtainable at platform.stability.ai) and an MCP client like Claude Desktop. Optionally set an image storage directory; the default is a temporary folder.

2

How much does each image generation cost?

Generating an image with the Core model costs 3 credits ($0.03 at $0.01/credit). Upscaling starts at $0.01, and more advanced tools range from $0.02 to $0.25 per operation. Pricing is pay-as-you-go.

3

Where are generated images saved?

All processed images are saved to the `IMAGE_STORAGE_DIRECTORY` (default: `/tmp/tadasant-mcp-server-stability-ai` on macOS/Linux or equivalent on Windows). They are also made available as resources in the MCP client.

4

Is this server officially affiliated with Stability AI?

No, this project is NOT officially affiliated with Stability AI.

5

Can I use this server with other MCP clients besides Claude Desktop?

It is built and tested on macOS with Claude Desktop, but it should work with other MCP clients as well.

评论

其他 分类下的更多 MCP 服务器

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

广告合作