MCP Server implementation for recraft.ai API
MCP Recraft Server connects MCP Recraft Server to AI assistants that speak the Model Context Protocol. MCP Server implementation for recraft.ai API.
This is an MCP (Model Context Protocol) server integrating MCP clients with Recraft's raster- and vector-image operations:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| style | size |
| model | number of images | \$0.04/\$0.08 per raster/vector image | |
| prompt | similarity strength |
| generate_image | Generates raster/vector images from prompt |
| create_style | Creates a style from the list of images |
| vectorize_image | Vectorizes raster image |
| image_to_image | Generates raster/vector images from image and prompt |
| remove_background | Removes background in image |
| replace_background | Generates new background in image from prompt |
| crisp_upscale | Crisp upscale of image |
| creative_upscale | Creative upscale of image |
| get_user | Get information about the user and left balance |
{
"mcpServers": {
"recraft": {
"command": "npx",
"args": [
"-y",
"@recraft-ai/mcp-recraft-server@latest"
],
"env": {
"RECRAFT_API_KEY": "<YOUR_RECRAFT_API_KEY>",
"IMAGE_STORAGE_DIRECTORY": "<YOUR_IMAGE_STORAGE_DIRECTORY>",
"RECRAFT_REMOTE_RESULTS_STORAGE": "<YOUR_REMOTE_RESULTS_STORAGE_INDICATOR>"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| RECRAFT_API_KEY | Credential the server authenticates with. | Yes |
| IMAGE_STORAGE_DIRECTORY | Filesystem location the server is allowed to use. | Optional |
| RECRAFT_REMOTE_RESULTS_STORAGE | Configuration value read at startup. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Hybrid search over your local documents, with file and page citations. One binary, fully local.
Add to `~/.gemini/settings.json` (user scope) or `.gemini/settings.json` (project scope):
Work-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery
An MCP (Model Context Protocol) server for integrating with Gelato's print-on-demand API. This server provides tools and resources to search orders