Stability AI MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GCS_PROJECT_ID | No | Google Cloud Project ID for storing images (when using SSE mode) | |
| GCS_BUCKET_NAME | No | Google Cloud Storage bucket name for storing images (when using SSE mode) | |
| GCS_PRIVATE_KEY | No | Google Cloud Service Account private key for storing images (when using SSE mode) | |
| GCS_CLIENT_EMAIL | No | Google Cloud Service Account client email for storing images (when using SSE mode) | |
| STABILITY_AI_API_KEY | Yes | Your Stability AI API key. Get one at platform.stability.ai | |
| IMAGE_STORAGE_DIRECTORY | No | Directory where generated images will be saved | /tmp/tadasant-mcp-server-stability-ai (or C:\Windows\Temp\mcp-server-stability-ai on Windows) |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| generate-image-from-text | Generate a new image with configurable description, style, and aspect ratio |
| generate-image-from-sketch | Generate an image from a hand-drawn sketch |
| generate-image-in-the-style-of | Generate an image in the style of an existing image |
| generate-image-using-structure | Generate an image while maintaining the structure (i.e. background, context) of a reference image |
| upscale-image | Upscale the quality of an image |
| edit-image | Make a minor modification to an existing image |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| .git | |
| .github | |
| .gitignore | |
| CHANGELOG.md | |
| CONTRIBUTING.md | |
| LICENSE | |
| README.md | |
| images | |
| node_modules | |
| package-lock.json | |
| package.json | |
| pnpm-lock.yaml | |
| src | |
| tsconfig.json |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| stability-ai-generate-image | Generate an image of anything based on a provided prompt. |
| stability-ai-generate-image-sd35 | Generate an image using Stable Diffusion 3.5 models with advanced configuration options. |
| stability-ai-remove-background | Remove the background from an image. |
| stability-ai-outpaint | Extends an image in any direction while maintaining visual consistency. |
| stability-ai-search-and-replace | Replace objects or elements in an image by describing what to replace and what to replace it with. |
| stability-ai-upscale-fast | Cheap and fast tool to enhance image resolution by 4x. |
| stability-ai-upscale-creative | Enhance image resolution up to 4K using AI with creative interpretation. This tool works best on highly degraded images and performs heavy reimagining. In general, don't use this (expensive) tool unless specifically asked to do so, usually after trying stability-ai-upscale-fast first. |
| stability-ai-control-sketch | Translate hand-drawn sketches to production-grade images. |
| stability-ai-0-list-resources | Use this to check for files before deciding you don't have access to a file or image or resource. It pulls in a list of all of user's available Resources (i.e. image files and their URI's) so we can reference pre-existing images to manipulate or upload to Stability AI. |
| stability-ai-search-and-recolor | Search and recolor object(s) in an image |
| stability-ai-replace-background-and-relight | Replace background and adjust lighting of an image |
| stability-ai-control-style | Generate a new image in the style of a reference image |
| stability-ai-control-structure | Generate a new image while maintaining the structure of a reference image |