Recraft MCP Server

What does “Recraft” MCP Server do?

The Recraft MCP Server is a Model Context Protocol (MCP) server that connects AI assistants and clients to the Recraft AI platform, enabling advanced raster and vector image operations through a standardized interface. It allows AI systems to generate and edit images, apply custom styles, perform vectorization, remove backgrounds, and upscale images by leveraging Recraft’s powerful APIs. This integration helps streamline development workflows involving image generation and editing, enabling tasks like automated asset creation, design prototyping, and batch image processing. By exposing these capabilities as MCP tools, developers can easily incorporate high-quality image manipulation into their AI-driven applications and workflows.

List of Prompts

No information about prompt templates is provided in the repository.

List of Resources

No explicit list of MCP resources is provided in the repository.

List of Tools

• generate_image: Generates raster or vector images from a prompt. Parameters include prompt, style, size, model, and number of images.
• image_to_image: Creates raster or vector images from an input image and prompt. Parameters include the input image, prompt, similarity strength, style, size, model, and number of images.
• create_style: Builds a new image style from a provided list of images.

Use Cases of this MCP Server

• Automated Marketing Asset Creation: Developers can automatically generate high-quality vector and raster images for marketing materials, reducing manual design workload.
• Custom Style Prototyping: Design teams can create and test custom visual styles by training on sample images, accelerating creative workflows.
• Image Vectorization and Upscaling: The server enables conversion of raster images to vectors and upscaling, useful for preparing assets for high-resolution print or web.
• Background Removal and Editing: Integrates advanced background removal and replacement into AI-powered pipelines, ideal for ecommerce or content creation.
• Batch Image Generation: Facilitates generating multiple images at scale based on prompts or style guides for product catalogs or datasets.

How to set it up

Windsurf

1. Ensure Node.js is installed.
2. Open your Windsurf configuration file.
3. Add the Recraft MCP Server to the mcpServers section using the following JSON:

   {
     "recraft-mcp": {
       "command": "npx",
       "args": ["@recraft-ai/mcp-recraft-server@latest"]
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the server is running via the Windsurf interface.

Claude

1. Ensure Node.js is available.
2. Open the Claude configuration panel.
3. Insert the Recraft MCP Server configuration:

   {
     "mcpServers": {
       "recraft-mcp": {
         "command": "npx",
         "args": ["@recraft-ai/mcp-recraft-server@latest"]
       }
     }
   }
   

4. Save your settings and restart Claude.
5. Confirm MCP server availability in the Claude dashboard.

Cursor

1. Install Node.js if not already present.
2. Go to Cursor’s settings and locate the MCP Servers section.
3. Add this JSON snippet:

   {
     "recraft-mcp": {
       "command": "npx",
       "args": ["@recraft-ai/mcp-recraft-server@latest"]
     }
   }
   

4. Save and restart Cursor.
5. Test image generation to confirm setup.

Cline

1. Verify Node.js installation.
2. Edit your Cline configuration file.
3. Add the following MCP server entry:

   {
     "recraft-mcp": {
       "command": "npx",
       "args": ["@recraft-ai/mcp-recraft-server@latest"]
     }
   }
   

4. Save changes and restart Cline.
5. Check for MCP server status.

Securing API Keys

To securely handle API keys, use environment variables in your configuration. Example:

{
  "recraft-mcp": {
    "command": "npx",
    "args": ["@recraft-ai/mcp-recraft-server@latest"],
    "env": {
      "RECRAFT_API_KEY": "your-api-key"
    },
    "inputs": {
      "api_key": "${RECRAFT_API_KEY}"
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "recraft-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “recraft-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between the provided details and documentation, the Recraft MCP Server is well-documented in terms of its tools and integration but lacks explicit prompt and resource definitions, as well as sampling or roots support. The setup process is clearly described, and tools are well-defined, making it easy to use for image-related workflows. Overall, I’d rate this MCP server a 6/10, mainly due to missing resource and prompt details.

MCP Score