Freepik MCP
Enables AI assistants to search, download, and generate visual content using Freepik APIs, including icon search, image generation, and resource management.
README
Freepik MCP
🚀 MCP Server for seamless Freepik API integration
🎯 What is this?
A Model Context Protocol (MCP) server that connects your AI assistants (Claude, Cursor, etc.) directly with Freepik's powerful APIs. Generate, search, and manage visual content without leaving your AI workflow.
🛠️ What tools are available?
- 🎨 Icon Search & Download - Find and download icons in multiple formats
- 📁 Resource Management - Access and manage multimedia content
- 🤖 AI Image Classification - Automatically classify and analyze images
- 🖼️ Image Generation - Create custom images using Mystic AI
📋 Prerequisites
Before you start, make sure you have:
- Python 3.12+ installed
- uv dependency manager (install here)
- Freepik API Key (get yours here)
🚀 Installation
1. Clone and navigate
git clone <REPOSITORY_URL>
cd freepik-mcp
2. Install using Makefile
# Install dependencies
make install
# Verify installation
make version
3. Configure your API Key
echo "FREEPIK_API_KEY=your_api_key_here" > .env
💡 Get your API Key at: freepik.com/api
⚙️ Configuration for AI Assistants
For Claude Desktop or Cursor on Linux
Add this to your config.json file:
⚠️ For Windows users: If you're on Windows, you need to use WSL (Windows Subsystem for Linux) to run this MCP server.
{
"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 Configuration Steps
-
Find your full path:
pwd # Copy the output and replace /FULL/PATH/TO/ in the config -
Replace with your API key:
- Get it from freepik.com/api
- Replace
your_actual_api_key_here
🏃♂️ Quick Start
# Development mode (auto-reload)
make dev
# Production mode
make run
# Check code quality
make lint
# Format code
make format
# Clean temporary files
make clean
# See all commands
make help
🤝 Contributing
We welcome contributions! Please follow these guidelines:
📝 Commit Convention
This project uses Conventional Commits. Format your commits as:
<type>(<scope>): <description>
[optional body]
[optional footer(s)]
Types:
feat: New featurefix: Bug fixdocs: Documentation changesstyle: Code style changes (formatting, etc.)refactor: Code refactoringtest: Adding or updating testschore: Maintenance tasks
Examples:
feat(icons): add search filtering by category
fix(api): resolve authentication timeout issue
docs(readme): update installation instructions
refactor(mystic): improve error handling logic
🔄 Contribution Workflow
- Fork the repository
- Create a feature branch:
git checkout -b feat/amazing-feature - Commit using conventional format:
git commit -m "feat: add amazing feature" - Push to your branch:
git push origin feat/amazing-feature - Open a Pull Request
📚 Development Commands
| Command | Description |
|---|---|
make help |
Show all available commands |
make install |
Install dependencies |
make dev |
Run in development mode |
make run |
Run in production mode |
make lint |
Check code quality |
make format |
Format code automatically |
make clean |
Clean temporary files |
make version |
Check FastMCP version |
🛡️ Security
- ⚠️ Never commit your API Key
- ✅ Use
.envfiles for sensitive data - ✅ The
.envfile is in.gitignore
📖 API Documentation
For detailed API information:
🆘 Troubleshooting
Common issues:
- "Command not found" → Install
uvdependency manager - "Invalid API Key" → Check your key at freepik.com/api
- "Path not found" → Verify the full path in your config
- "Connection refused" → Make sure the server is running with
make dev
Still having issues? Open an issue on GitHub with:
- Your OS and Python version
- Full error message
- Configuration file (without API key)
Ready to create amazing content with AI? 🎨✨
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。