
Kie.ai MCP Server
Enables AI-powered image generation and editing with Nano Banana, plus professional video creation with Veo3, all through Kie.ai's APIs. Includes task tracking, status monitoring, and 1080p video upgrades.
README
Kie.ai MCP Server
An MCP (Model Context Protocol) server that provides access to Kie.ai's AI APIs including Nano Banana image generation/editing and Veo3 video generation.
Features
- Nano Banana Image Generation: Text-to-image generation using Google's Gemini 2.5 Flash Image Preview
- Nano Banana Image Editing: Natural language image editing with up to 5 input images
- Veo3 Video Generation: Professional-quality video generation with text-to-video and image-to-video capabilities
- 1080p Video Upgrade: Get high-definition versions of Veo3 videos
- Task Management: SQLite-based task tracking with status polling
- Smart Endpoint Routing: Automatic detection of task types for status checking
- Error Handling: Comprehensive error handling and validation
Prerequisites
- Node.js 18+
- Kie.ai API key from https://kie.ai/api-key
Installation
From NPM
npm install -g @andrewlwn77/kie-ai-mcp-server
From Source
# Clone the repository
git clone https://github.com/andrewlwn77/kie-ai-mcp-server.git
cd kie-ai-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
Configuration
Environment Variables
# Required
export KIE_AI_API_KEY="your-api-key-here"
# Optional
export KIE_AI_BASE_URL="https://api.kie.ai/api/v1" # Default
export KIE_AI_TIMEOUT="60000" # Default: 60 seconds
export KIE_AI_DB_PATH="./tasks.db" # Default: ./tasks.db
MCP Configuration
Add to your Claude Desktop or MCP client configuration:
{
"kie-ai-mcp-server": {
"command": "node",
"args": ["/path/to/kie-ai-mcp-server/dist/index.js"],
"env": {
"KIE_AI_API_KEY": "your-api-key-here"
}
}
}
Or if installed globally:
{
"kie-ai-mcp-server": {
"command": "npx",
"args": ["-y", "@andrewlwn77/kie-ai-mcp-server"],
"env": {
"KIE_AI_API_KEY": "your-api-key-here"
}
}
}
Available Tools
1. generate_nano_banana
Generate images using Nano Banana.
Parameters:
prompt
(string, required): Text description of the image to generate
Example:
{
"prompt": "A surreal painting of a giant banana floating in space"
}
2. edit_nano_banana
Edit images using natural language prompts.
Parameters:
prompt
(string, required): Description of edits to makeimage_urls
(array, required): URLs of images to edit (max 5)
Example:
{
"prompt": "Add a rainbow arching over the mountains",
"image_urls": ["https://example.com/image.jpg"]
}
3. generate_veo3_video
Generate videos using Veo3.
Parameters:
prompt
(string, required): Video descriptionimageUrls
(array, optional): Image for image-to-video (max 1)model
(enum, optional): "veo3" or "veo3_fast" (default: "veo3")aspectRatio
(enum, optional): "16:9" or "9:16" (default: "16:9")seeds
(integer, optional): Random seed 10000-99999watermark
(string, optional): Watermark textenableFallback
(boolean, optional): Enable fallback mechanism
Example:
{
"prompt": "A dog playing in a park",
"model": "veo3",
"aspectRatio": "16:9",
"seeds": 12345
}
4. get_task_status
Check the status of a generation task.
Parameters:
task_id
(string, required): Task ID to check
5. list_tasks
List recent tasks with their status.
Parameters:
limit
(integer, optional): Max tasks to return (default: 20, max: 100)status
(string, optional): Filter by status ("pending", "processing", "completed", "failed")
6. get_veo3_1080p_video
Get 1080P high-definition version of a Veo3 video.
Parameters:
task_id
(string, required): Veo3 task ID to get 1080p video forindex
(integer, optional): Video index (for multiple video results)
Note: Not available for videos generated with fallback mode.
API Endpoints
The server interfaces with these Kie.ai API endpoints:
- Veo3 Video Generation:
POST /api/v1/veo/generate
✅ VALIDATED - Veo3 Video Status:
GET /api/v1/veo/record-info
✅ VALIDATED - Veo3 1080p Upgrade:
GET /api/v1/veo/get-1080p-video
✅ VALIDATED - Nano Banana Generation:
POST /api/v1/playground/createTask
✅ VALIDATED - Nano Banana Status:
GET /api/v1/playground/recordInfo
✅ VALIDATED
All endpoints have been tested and validated with live API responses.
Database Schema
The server uses SQLite to track tasks:
CREATE TABLE tasks (
id INTEGER PRIMARY KEY AUTOINCREMENT,
task_id TEXT UNIQUE NOT NULL,
api_type TEXT NOT NULL, -- 'nano-banana', 'nano-banana-edit', 'veo3'
status TEXT DEFAULT 'pending',
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
result_url TEXT,
error_message TEXT
);
Usage Examples
Basic Image Generation
# Generate an image
curl -X POST http://localhost:3000/tools/call \
-H "Content-Type: application/json" \
-d '{
"name": "generate_nano_banana",
"arguments": {
"prompt": "A cat wearing a space helmet"
}
}'
Video Generation with Options
# Generate a video
curl -X POST http://localhost:3000/tools/call \
-H "Content-Type: application/json" \
-d '{
"name": "generate_veo3_video",
"arguments": {
"prompt": "A peaceful garden with blooming flowers",
"aspectRatio": "16:9",
"model": "veo3_fast"
}
}'
Error Handling
The server handles these HTTP error codes from Kie.ai:
- 200: Success
- 400: Content policy violation / English prompts only
- 401: Unauthorized (invalid API key)
- 402: Insufficient credits
- 404: Resource not found
- 422: Validation error / record is null
- 429: Rate limited
- 451: Image access limits
- 455: Service maintenance
- 500: Server error / timeout
- 501: Generation failed
Development
# Run tests
npm test
# Development mode with auto-reload
npm run dev
# Type checking
npx tsc --noEmit
# Build for production
npm run build
Pricing
Based on Kie.ai documentation:
- Nano Banana: $0.020 per image (4 credits)
- Veo3 Quality: Higher cost tier
- Veo3 Fast: ~20% of Quality model pricing
See https://kie.ai/billing for detailed pricing.
Production Tips
- Database Location: Set
KIE_AI_DB_PATH
to a persistent location - API Key Security: Never commit API keys to version control
- Rate Limiting: Implement client-side rate limiting for high-volume usage
- Monitoring: Monitor task status and handle failed generations appropriately
- Storage: Consider automatic cleanup of old task records
Troubleshooting
Common Issues
"Unauthorized" errors
- Verify
KIE_AI_API_KEY
is set correctly - Check API key is valid at https://kie.ai/api-key
"Task not found" errors
- Tasks may expire after 14 days
- Check task ID format matches expected pattern
Generation failures
- Check content policy compliance
- Verify prompt is in English
- Ensure sufficient API credits
Support
For issues related to:
- MCP Server: Open an issue at https://github.com/andrewlwn77/kie-ai-mcp-server/issues
- Kie.ai API: Contact support@kie.ai or check https://docs.kie.ai/
- API Keys: Visit https://kie.ai/api-key
License
MIT License - see LICENSE file for details.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
Changelog
v1.0.0
- Initial release
- Nano Banana image generation and editing
- Veo3 video generation
- 1080p video upgrade support
- SQLite task tracking
- Smart endpoint routing
- Comprehensive error handling
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。