Stability AI

The Stability AI MCP Server lets you connect MCP clients to Stability AI’s image manipulation capabilities (generate, edit, upscale, and more) via a simple, low-friction setup. By providing an API key, you can generate high‑quality images and perform a range of edits directly from your MCP client, with results saved locally for quick access and preview.

How to use

You use this MCP server from an MCP client (such as Claude Desktop) to perform image generation and manipulation tasks through Stability AI’s REST API. Start by supplying your Stability AI API key and choosing a local directory to store generated images. Images are automatically saved, opened for preview, and exposed as chat resources you can reuse in your conversations.

How to install

Prerequisites you need before installation are Node.js and an MCP client (for example Claude Desktop). Install Node.js from the official site if you don’t have it already.

Choose one of the following installation paths and follow the steps exactly as shown.

// Manual setup for Claude Desktop (local stdio MCP server)

{
  "mcpServers": {
    "stability-ai": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-stability-ai"
      ],
      "env": {
        "STABILITY_AI_API_KEY": "sk-1234567890"
      }
    }
  }
}

Additional installation paths

If you prefer to install via Smithery for Claude Desktop, run the following command to set up automatically.

npx @smithery/cli install mcp-server-stability-ai --client claude

SSE mode for multi‑tenant HTTP deployment

If you want to deploy this server for third‑party usage over HTTP, you can run it in SSE mode. Use the following command to start the server with SSE enabled.

npx mcp-server-stability-ai -y --sse

Prerequisites and environment variables

Prepare a folder on your machine to store generated/modified images and set your Stability AI API key. The server also supports optional metadata logging and Google Cloud Storage for SSE mode when configured.

Available tools

generate-image

Generate a high quality image from a prompt with optional parameters such as style, aspect ratio, and model selection.

generate-image-sd35

Generate using Stable Diffusion 3.5 models with advanced configuration options.

remove-background

Remove the background from the current image to create a transparent or foreground-focused result.

outpaint

Extend an image in any direction while maintaining visual consistency.

search-and-replace

Replace objects or elements in an image by describing what to replace and what to replace it with.

upscale-fast

Increase image resolution by 4x with a quick quality enhancement.

upscale-creative

Improve resolution up to 4K with enhanced quality and detail.

control-sketch

Translate a hand-drawn sketch into a production-grade image.

control-style

Generate an image in the style of a reference image.

control-structure

Generate an image while maintaining the structure of a reference image.

replace-background-and-relight

Replace the background and re-light the image for a cohesive result.

search-and-recolor

Find and recolor objects within an image.