mcp -stability-ai
MCP Server integrating MCP Clients with Stability AI-powered image manipulation functionalities: generate, edit, upscale, and more.
claude mcp add --transport stdio tadasant-mcp-server-stability-ai node server.js \ --env STABILITY_API_KEY="your-stability.ai-api-key" \ --env IMAGE_STORAGE_DIRECTORY="./output-images"
How to use
This MCP server provides an integration with Stability AI's image generation and manipulation capabilities. After starting the server, you can interact with a set of image tools such as generate-image, generate-image-sd35, remove-background, outpaint, search-and-replace, and various upscaling and control tools. The server surfaces these tools through your MCP client (e.g., Claude Desktop or another MCP client) and handles communication with Stability AI's hosted API using your API key. Processed images are saved locally to the configured IMAGE_STORAGE_DIRECTORY and shown as resources within the client workflow. The toolset enables chaining operations in a single conversation, such as generating an image, applying an edit, and then upscaling or relighting, all while keeping outputs organized in the local storage folder.
How to install
Prerequisites:
- Node.js (>= 14.x) and npm installed on your machine
- A Stability AI API key (sign up at stability.ai and generate an API key)
Steps:
- Clone the repository or download the MCP server package.
- Install dependencies: npm install
- Create an environment file or export environment variables for your run:
- STABILITY_API_KEY: your Stability AI API key
- IMAGE_STORAGE_DIRECTORY: path to store generated images, e.g. ./output-images
- Start the server: npm start (or run: node server.js if the entry file is named server.js)
Notes:
- Ensure the IMAGE_STORAGE_DIRECTORY exists and is writable by the process.
- If you customize the server entry point or port, adjust the command accordingly in the mcp_config.
Additional notes
Tips and common considerations:
- Keep your Stability AI API key secure; do not expose it in public repositories.
- The server saves all outputs to IMAGE_STORAGE_DIRECTORY, which can grow quickly; monitor disk usage or configure rotation/cleanup if needed.
- If you encounter rate limits or API errors, review your Stability AI plan and verify the API key permissions.
- Some clients may require explicit prompts or presets; utilize the built-in prompts/assets shown in the README for best results.
- Validate that the environment variables are correctly loaded by checking the server logs on startup.
Related MCP Servers
iterm
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
mcp
Octopus Deploy Official MCP Server
furi
CLI & API for MCP management
editor
MCP Server for Phaser Editor
DoorDash
MCP server from JordanDalton/DoorDash-MCP-Server
mcp
MCP сервер для автоматического создания и развертывания приложений в Timeweb Cloud