How do I obtain a Recraft API key?
Register an account at Recraft.ai, go to your profile API page, buy API units (credits), and generate an API key.
@recraft-ai
Basic information
MCP (modelcontextprotocol) server implementation for Recraft API
Add this server to your MCP-compatible client using the configuration below.
{
"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>"
}
}
}
}Generate an image using Recraft from a text prompt. You can specify the image size, style, model, and number of images to generate. You don't need to change default parameters if you don't have any specific requirements. You can use styles to refine the image generation, and also to generate raster or vector images. Local paths or URLs to generated images and their previews will be returned in the response.
Create a style in Recraft from the set of style reference images. A style is extracted from the provided images and can be used in image generation tools. ID of the created style will be returned in the response.
Vectorize an input image using Recraft. This operation takes an input image and returns a vector SVG image, close to it. Local path or URL to resulting image and its preview will be returned in the response.
Generate an image using Recraft from an input image and a text prompt. You can specify the reference input image, style, model, and number of images to generate. You should provide the same style/substyle/styleID settings as were used for input image generation (if exists) if there are no specific requirements to change the style. Other parameters are recommended to keep default if you don't have any specific requirements on them. You can use styles to refine the image generation, and also to generate raster or vector images. Local paths or URLs to generated images and their previews will be returned in the response.
Remove background in the input image using Recraft. This operation takes an input image and returns the same image with detected background removed. Raster image will be always returned. Local path or URL to resulting image and its preview will be returned in the response.
Generate an image using Recraft from an input image with its detected background replaced based on the prompt. You can specify the input image, style, model, and number of images to generate. You should provide the same style/substyle/styleID settings as were used for input image generation (if exists) if there are no specific requirements to change the style. Other parameters are recommended to keep default if you don't have any specific requirements on them. You can use styles to refine the image background generation, and also to generate raster or vector images. Local paths or URLs to generated images and their previews will be returned in the response.
Crisp upscale of the input image using Recraft. This operation takes an input image and returns an upscaled image, making the image sharper and cleaner. This version of upscale is much cheaper and faster than creative upscale. Local path or URL to resulting image and its preview will be returned in the response.
Creative upscale of the input image using Recraft. This operation takes an input image and returns an upscaled image, boosting resolution with a focus on refining small details and faces. This version of upscale is expensive and slower than crisp upscale. Local path or URL to resulting image and its preview will be returned in the response.
Get information about the current Recraft API user (their email, name, and credit balance).
Mcp Recraft Server is an MCP (Model Context Protocol) server that integrates MCP clients with Recraft’s raster- and vector-image operations. It enables image generation, editing, style creation, vectorization, background removal and replacement, and upscaling for developers and AI‑assisted workflows.
Obtain a Recraft API key from your Recraft profile API page. Install via Claude Desktop Extensions (download the .dxt file and double‑click), via Smithery (remote storage only), or manually by editing claude_desktop_config.json with npx or a built source. Configure the environment variables RECRAFT_API_KEY (mandatory), IMAGE_STORAGE_DIRECTORY (optional, defaults to $HOME_DIR/.mcp-recraft-server), and RECRAFT_REMOTE_RESULTS_STORAGE (set to "1" for remote storage).
Register an account at Recraft.ai, go to your profile API page, buy API units (credits), and generate an API key.
You can install via Claude Desktop Extensions (download `.dxt` file), via Smithery (remote storage only), or manually by editing `claude_desktop_config.json` using `npx` or a local build.
Set the `IMAGE_STORAGE_DIRECTORY` environment variable for local storage (defaults to `$HOME_DIR/.mcp-recraft-server`), or set `RECRAFT_REMOTE_RESULTS_STORAGE="1"` to store images remotely and receive URLs.
It provides nine tools: `generate_image`, `create_style`, `vectorize_image`, `image_to_image`, `remove_background`, `replace_background`, `crisp_upscale`, `creative_upscale`, and `get_user`. Each tool has specific parameters and per‑image pricing.
Manual setup requires Node.js to run `npx` or `node`. The server communicates over stdio and requires a Recraft API key for authentication.
Painless E2E Automation for Mobile and Web
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Hindsight: Agent Memory That Learns
Comments