Recraft AI logo

Recraft AI

Organization
recraft-ai

MCP (modelcontextprotocol) server implementation for Recraft API

Publisherrecraft-ai
Repositorymcp-recraft-server
LanguageTypeScript
Forks
9
Stars
55
Available tools
0
Transport typestdio
Categories
LicenseMIT
Links
  • Connect tools to AI workflows

    Recraft AI exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    55 stars and 9 forks from the linked repository.

This is an MCP (Model Context Protocol) server integrating MCP clients with Recraft's raster- and vector-image operations:

  • raster and vector image generation
  • raster and vector image 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.

Table of Contents

Setup

Prerequisites

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

  • You will need to have an MCP client installed, for example Claude Desktop.

Claude Desktop Extensions

If you are using Claude Desktop you can set up this server using Claude Desktop Extensions.

  • Download mcp-recraft-server.dxt from the latest release
  • Double-click the file to open it with Claude Desktop
  • Click Install
  • Fill out the form
  • Enable the server

In the form you need to paste your Recraft API key obtained on your profile API page. You can also specify a local path for generated image storage or indicate that all results should be stored remotely.

In case of installation issues, check that you have the latest version of Claude Desktop.

Smithery

You can find this MCP server on Smithery. If this MCP is installed from Smithery, all generation results will be stored remotely. Use Desktop Extensions or Manual Setup to store generation results on your local device.

Manual Setup

You're going to need Node running 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.

From NPM

Modify your claude_desktop_config.json file to add the following:

json
{
  "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>"
      }
    }
  }
}

From source

Clone this repository:

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

In the directory with cloned repository run:

bash
npm install
npm run build

Modify your claude_desktop_config.json file to add the following:

json
{
  "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>",
        "RECRAFT_REMOTE_RESULTS_STORAGE": "<YOUR_REMOTE_RESULTS_STORAGE_INDICATOR>"
      }
    }
  }
}

You can specify these parameters:

  • RECRAFT_API_KEY: mandatory parameter, your Recraft 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. If RECRAFT_REMOTE_RESULTS_STORAGE="1", the value of this parameter is ignored.
  • RECRAFT_REMOTE_RESULTS_STORAGE: optional parameter, you can set the value to "1", in this case all generated images will be stored remotely and their URLs will be returned. Also, IMAGE_STORAGE_DIRECTORY will be ignored in this case.

Tools

In this MCP you can use the following tools:

Tool NameDescriptionParametersPrice
generate_imageGenerates raster/vector images from prompt- prompt - style - size - model - number of images$0.04/$0.08 per raster/vector image
create_styleCreates a style from the list of images- list of images - basic style$0.04
vectorize_imageVectorizes raster image- image$0.01
image_to_imageGenerates raster/vector images from image and prompt- image - prompt - similarity strength - style - size - model - number of images$0.04/$0.08 per raster/vector image
remove_backgroundRemoves background in image- image$0.01
replace_backgroundGenerates new background in image from prompt- image - prompt for background - style - size - model - number of images$0.04/$0.08 per raster/vector image
crisp_upscaleCrisp upscale of image- image$0.004
creative_upscaleCreative upscale of image- image$0.25
get_userGet information about the user and left balance

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

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "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>"
      }
    }
  }
}

Use Recraft AI MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Recraft AI is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Recraft AI as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Recraft AI MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "recraft-ai": {
      "command": "npx",
      "args": [
        "-y",
        "@recraft-ai/mcp-recraft-server"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Recraft AI MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Recraft AI MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Recraft AI to help me with this task?
Recraft AI
Sure. I read it.
Here is what I found using Recraft AI.

Frequently asked questions

What is the Recraft AI MCP server used for?

Recraft AI is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Recraft AI MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Recraft AI with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Recraft AI MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Recraft AI connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Recraft AI MCP to TypingMind?

Recraft AI runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Recraft AI MCP provide in TypingMind?

Recraft AI exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Recraft AI MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Recraft AI requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇