Stability AI
An MCP Server that integrates with Stability AI's API to provide high-quality image generation, editing, and manipulation capabilities including background removal, outpainting, search-and-replace, and upscaling.
What is Stability AI?
Stability AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that integrates with stability ai's api to provide high-quality image generation, editing, and manipulation capabilities including background removal, outpainting, search-and-replace, and u...
An MCP Server that integrates with Stability AI's API to provide high-quality image generation, editing, and manipulation capabilities including background removal, outpainting, search-and-replace, and upscaling.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP Server that integrates with Stability AI's API to pro
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx stability-ai-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Stability AI
The Stability AI MCP Server connects AI assistants like Claude directly to Stability AI's image generation and editing API, exposing 12 distinct image tools including text-to-image generation, background removal, outpainting, search-and-replace, upscaling, and relighting. It lets you describe images in natural language and receive generated or modified images without leaving your chat interface. Developers and designers use it to prototype visual assets, automate image workflows, and apply precise edits like replacing backgrounds or extending canvas boundaries — all through conversational prompts.
Prerequisites
- Node.js 18 or later installed on your system
- A Stability AI account with an active API key (obtainable at platform.stability.ai)
- An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
- Optionally, a local directory path for storing generated images
Get your Stability AI API key
Sign in at platform.stability.ai, navigate to API Keys, and generate a new key. Copy the key value — it starts with 'sk-'. Keep it secret; you will set it as an environment variable in the MCP config.
Add the server to your MCP client config
Open your MCP client configuration file (for Claude Desktop on macOS: ~/Library/Application Support/Claude/claude_desktop_config.json) and add the stability-ai server entry with your API key.
{
"mcpServers": {
"stability-ai": {
"command": "npx",
"args": ["-y", "mcp-server-stability-ai"],
"env": {
"STABILITY_AI_API_KEY": "sk-your-api-key-here"
}
}
}
}Optionally configure image storage
By default, generated images are saved to a temporary directory. Set IMAGE_STORAGE_DIRECTORY to an absolute path on your machine to control where images land. Set SAVE_METADATA to false if you do not want sidecar JSON files alongside each image.
"env": {
"STABILITY_AI_API_KEY": "sk-your-api-key-here",
"IMAGE_STORAGE_DIRECTORY": "/Users/you/Pictures/stability-output",
"SAVE_METADATA": "true"
}Restart your MCP client
Save the config file and restart Claude Desktop (or reload the MCP server list in your client). The stability-ai server should appear as connected and its 12 tools will become available.
Generate your first image
Open a new conversation in your MCP client and ask Claude to generate an image. The generate-image tool calls the Stability AI API and returns the image file path or renders it inline, depending on your client.
Stability AI Examples
Client configuration
Minimal Claude Desktop configuration to enable all 12 Stability AI image tools.
{
"mcpServers": {
"stability-ai": {
"command": "npx",
"args": ["-y", "mcp-server-stability-ai"],
"env": {
"STABILITY_AI_API_KEY": "sk-your-api-key-here",
"IMAGE_STORAGE_DIRECTORY": "/tmp/stability-images",
"SAVE_METADATA": "true"
}
}
}
}Prompts to try
Example prompts that exercise the main image capabilities of this server.
- "Generate a photorealistic image of a cat sitting in a cyberpunk city at night with neon lights reflecting off wet pavement"
- "Remove the background from product-photo.jpg and make it transparent"
- "Extend vacation-photo.jpg by 500 pixels to the right using outpainting"
- "In portrait.png, replace the plain white wall behind the subject with a sunset over the mountains"
- "Upscale logo.png to 4x resolution using the creative upscaler"
- "Search for the red car in scene.jpg and recolor it to bright blue"Troubleshooting Stability AI
Error: STABILITY_AI_API_KEY is not set or invalid
Double-check the API key in your config file — it must start with 'sk-'. Confirm the key is active in your Stability AI dashboard and has not been revoked. Restart Claude Desktop after updating the config.
Generated images are not saved or cannot be found
Set IMAGE_STORAGE_DIRECTORY to an absolute directory path that already exists and is writable. If omitted, images land in a system temp directory that may be cleared on reboot.
Tool call fails with 'insufficient credits'
Stability AI image operations consume credits. Log in to platform.stability.ai to check your credit balance and purchase more if needed. Some tools (creative upscale, relighting) cost more credits than basic generation.
Frequently Asked Questions about Stability AI
What is Stability AI?
Stability AI is a Model Context Protocol (MCP) server that mcp server that integrates with stability ai's api to provide high-quality image generation, editing, and manipulation capabilities including background removal, outpainting, search-and-replace, and upscaling. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Stability AI?
Follow the installation instructions on the Stability AI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Stability AI?
Stability AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Stability AI free to use?
Yes, Stability AI is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Stability AI Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Stability AI? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Stability AI in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Stability AI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.