Freepik

You can run a dedicated MCP server that connects your AI assistants directly to Freepik’s APIs, enabling you to generate, search, and manage visuals without leaving your workflow. This server acts as a bridge between your AI tools and Freepik, handling requests securely with your API key and supporting a smooth, automated content-creation experience.

How to use

Launch the Freepik MCP server from your environment and connect it to your MCP client. You will typically run the server in stdio mode so it starts as a local process, and you will configure your client to point at the running MCP server. The server exposes tools that let you search for icons, manage multimedia resources, classify images, and generate new visuals through Freepik APIs. Ensure you provide your Freepik API key in environment variables and reference it when starting the server.

How to install

Prerequisites: make sure you have Python 3.12 or newer and the uv dependency manager installed. You also need a Freepik API Key.

Step 1: Clone the repository and navigate into the project directory.

git clone <REPOSITORY_URL>
cd freepik-mcp

Step 2: Install dependencies and verify the installation.

make install
make version

Step 3: Configure your API Key by setting it in a .env file.

echo "FREEPIK_API_KEY=your_api_key_here" > .env

Step 4: Prepare the MCP client configuration to run the server locally. The following example shows how to run the MCP using uv with the full directory path to the server and the main script.

{
  "mcpServers": {
    "freepik-fastmcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/FULL/PATH/TO/freepik-mcp",
        "main.py"
      ],
      "env": {
        "FREEPIK_API_KEY": "your_actual_api_key_here"
      }
    }
  }
}

Important: replace "/FULL/PATH/TO/freepik-mcp" with your actual full path to the project directory and replace the API key placeholder with your real Freepik API key.

Additional setup and configuration notes

Find your full path in the shell and replace the placeholder in the configuration accordingly.

Replace the API key placeholder with the actual key you obtain from Freepik at freepik.com/api.

Security and maintenance

Never commit your API key. Use a .env file for sensitive data and ensure it is included in your .gitignore.

Use the built-in project commands to maintain code quality, format, and clean up temporary files, and keep dependencies up to date.

Troubleshooting

Common issues and fixes include:

• Command not found: Install the uv dependency manager.
• Invalid API Key: Check your Freepik API key at freepik.com/api.
• Path not found: Verify the full path in your config.
• Connection refused: Ensure the server is running with the development command.

If problems persist, collect your OS details, Python version, the exact error message, and the configuration file (excluding the API key) and seek help with those details.

Example configuration for the MCP client

Use this configuration in your MCP client to point to the local Freepik MCP server in stdio mode.

{
  "mcpServers": {
    "freepik-fastmcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/FULL/PATH/TO/freepik-mcp",
        "main.py"
      ],
      "env": {
        "FREEPIK_API_KEY": "your_actual_api_key_here"
      }
    }
  }
}

Notes

This MCP server is designed to connect your AI assistants to Freepik APIs for icon search, resource management, AI image classification, and image generation. Ensure your environment has the required Python version and uv tool, and protect your API key at all times.

Available tools

Icon Search & Download

Find and download icons in multiple formats using Freepik APIs.

Resource Management

Access and manage multimedia content within your workflow.

AI Image Classification

Automatically classify and analyze images using AI capabilities.

Image Generation

Create custom images using Freepik integrated generation features.