Recraft Ai_mcp Recraft Server

by MCP-Mirror

298 downloads
Not rated
GitHub

About

This MCP server integrates MCP Clients with Recraft AI’s raster and vector image operations, including generation, editing, custom styles, vectorization, background removal/replacement, and upscaling. It is designed for developers and users who want to generate or edit…

Details

Author
MCP-Mirror
Downloads
298
Categories
Other

- Generate raster and vector images from text prompts
- Edit images using image-to-image with similarity control
- Create custom styles from a set of images
- Vectorize raster images with one tool
- Remove or replace backgrounds in images
- Upscale images in crisp or creative modes

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Recraft Ai_mcp Recraft Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Obtain a Recraft AI API key, install Node.js, and have an MCP client (e.g., Claude Desktop). Install the server via npx -y @recraft-ai/mcp-recraft-server or clone the repository and build from source. Configure your MCP client’s JSON file with RECRAFT_API_KEY (required) and optionally IMAGE_STORAGE_DIRECTORY.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "recraft ai_mcp recraft server": {
            "recraft": {
                "command": "npx",
                "args": [
                    "-y",
                    "@recraft-ai/mcp-recraft-server"
                ],
                "env": {
                    "RECRAFT_API_KEY": "<YOUR_RECRAFT_API_KEY>",
                    "IMAGE_STORAGE_DIRECTORY": "<YOUR_IMAGE_STORAGE_DIRECTORY>"
                }
            }
        }
    }
}

McpServers

{
    "recraft": {
        "command": "npx",
        "args": [
            "-y",
            "@recraft-ai/mcp-recraft-server"
        ],
        "env": {
            "RECRAFT_API_KEY": "<YOUR_RECRAFT_API_KEY>",
            "IMAGE_STORAGE_DIRECTORY": "<YOUR_IMAGE_STORAGE_DIRECTORY>"
        }
    }
}

<div align="center">
<h1>

<br/>Recraft AI MCP Server
</h1>


npm version
npm downloads
</div>

This is an MCP (Model Context Protocol) Server integrating MCP Clients with Recraft AI's raster and vector image operations:

- raster and vector images generation
- raster and vector images editing
- creating custom styles and generating images in them
- vectorization of raster images
- background removal and replacement
- upscaling of raster images

By connecting this MCP Server to your MCP Client you will be able to generate high-quality raster and vector images using Recraft, combining different tools.

Tools

In this MCP you can use the following tools:

| Tool Name | Description | Parameters | Price |
|-----------|-------------|------------|-------|
| generate_image | Generates raster/vector images from prompt | - prompt <br/> - style <br/> - size <br/> - model <br/> - number of images | \$0.04/\$0.08 per raster/vector image |
| image_to_image | Generates raster/vector images from image and prompt | - image <br/> - prompt <br/> - similarity strength <br/> - style <br/> - size <br/> - model <br/> - number of images | \$0.04/\$0.08 per raster/vector image |
| create_style | Creates a style from the list of images | - list of images <br/> - basic style | \$0.04 |
| vectorize_image | Vectorizes raster image | - image | \$0.01 |
| remove_background | Removes background in image | - image | \$0.01 |
| replace_background | Generates new background in image from prompt | - image <br/> - prompt for background <br/> - style <br/> - size <br/> - model <br/> - number of images | \$0.04/\$0.08 per raster/vector image |
| crisp_upscale | Crisp upscale of image | - image | \$0.004 |
| creative_upscale | Creative upscale of image | - image | \$0.25 |
| get_user | Get information about the user and left balance | | |

You can find the detailed explanation of tools, their parameters, and prices in Recraft AI API docs.

Setup

Prerequisites

- First of all, you will need a Recraft AI API key. To obtain it, register your account on Recraft AI, go to your profile API page. Here you can buy API units (credits), and generate an API key.

- You're going to need Node working on your machine so you can run npx or node commands in your terminal. If you don't have Node, you can install it from nodejs.org.

- You will need to have some MCP client installed, for example Claude Desktop.

Manual setup

Modify your claude_desktop_config.json file to add the following:

{
  "mcpServers": {
    "recraft": {
      "command": "npx",
      "args": [
        "-y",
        "@recraft-ai/mcp-recraft-server"
      ],
      "env": {
        "RECRAFT_API_KEY": "<YOUR_RECRAFT_API_KEY>",
        "IMAGE_STORAGE_DIRECTORY": "<YOUR_IMAGE_STORAGE_DIRECTORY>"
      }
    }
  }
}

Manual setup (from source)

Clone this repository:

git clone https://github.com/recraft-ai/mcp-recraft-server.git

In the directory with cloned repository run:

npm install
npm run build

Modify your claude_desktop_config.json file to add the following:

{
  "mcpServers": {
    "recraft": {
      "command": "node",
      "args": ["absolute path to cloned directory /dist/index.js"],
      "env": {
        "RECRAFT_API_KEY": "<YOUR_RECRAFT_API_KEY>",
        "IMAGE_STORAGE_DIRECTORY": "<YOUR_IMAGE_STORAGE_DIRECTORY>"
      }
    }
  }
}

You can specify these parameters:

- RECRAFT_API_KEY: mandatory parameter, your Recraft AI API key.
- IMAGE_STORAGE_DIRECTORY: optional parameter, you can specify the directory in which all generated images will be stored. By default this directory is $HOME_DIR/.mcp-recraft-server.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.