Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-xmorf Edit this image to remove the background"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for xmorf — AI image editing and generation API.
Tool | Description |
| Edit images with natural language prompts (8 AI models) |
| Generate images from text descriptions |
| List available editing models |
Model | Description |
| General-purpose AI image editing |
| Enhance realism / anything-to-real |
| Upscale and improve resolution |
| Light & shadow migration (needs reference image) |
| Passionate kiss effect (needs reference image) |
| Skin editing and retouching |
| Multi-angle view generation |
| Scene change / next-scene generation |
Related MCP server: image-forge-mcp
Get an API token from xmorf.com.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"xmorf": {
"command": "npx",
"args": ["-y", "mcp-xmorf"],
"env": {
"XMORF_API_TOKEN": "xmorf_your_token_here"
}
}
}
}Add to .vscode/mcp.json:
{
"servers": {
"xmorf": {
"command": "npx",
"args": ["-y", "mcp-xmorf"],
"env": {
"XMORF_API_TOKEN": "xmorf_your_token_here"
}
}
}
}Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"xmorf": {
"command": "npx",
"args": ["-y", "mcp-xmorf"],
"env": {
"XMORF_API_TOKEN": "xmorf_your_token_here"
}
}
}
}Edit this photo to remove the backgroundThe xmorf_edit_image tool accepts file paths, data URLs, or raw base64 as input. You can optionally specify an output path to save the result to disk.
Generate a watercolor painting of a mountain landscape at dawnWhat image editing models are available on xmorf?Variable | Required | Description |
| Yes | Your xmorf API bearer token |
See the full API docs at xmorf.com/docs.
MIT
Edit an image using AI with a natural language prompt. Models: standard (general-purpose), enhance (realism), upscale (resolution), shadow (light migration, needs reference), kiss (needs reference), skin (retouching), angles (multi-angle), scene (scene change). Input can be a file path or base64 data URL.
Inputs: image (required), prompt (required), model, referenceImage, +1 more.
Generate an image from a text description using AI
Inputs: prompt (required), model, size, outputPath.
List available xmorf image editing models and their descriptions
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a distinct purpose: generating images, editing images, and listing models. No ambiguity between them.
All tool names follow a consistent pattern: xmorf_verb_noun (edit_image, generate_image, list_models).
Three tools cover the core functionality (generate, edit, model info) without unnecessary clutter, well-scoped for the server's purpose.
The set covers the main operations (generation, editing, model listing). A minor gap could be a tool for deleting or retrieving generated images, but the core workflow is complete.
MCP server for Flux AI image generation
MCP server for Qwen Image 3 AI image generation
MCP server for Midjourney AI image generation and editing
MCP server for Grok Imagine AI video generation