xSkill AI
About
AI content generation toolkit with 50+ models. Image/video generation, TTS, voice cloning, and more.
Details
- Author
- hexiaochun
- Downloads
- 320
- Categories
- Developer Tools, AI
Jump to
- 50+ AI models including FLUX, Kling, Sora, and more
- Image generation (text-to-image and image-to-image)
- Video generation (text-to-video, image-to-video, Seedance 2.0)
- Text-to-speech synthesis with speed/pitch control
- Voice cloning from an audio sample
- Watermark-free video parsing from Douyin, Kuaishou, Bilibili
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
xSkill AICommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Obtain an API key from xskill.ai, then add the server configuration to your .cursor/mcp.json using the provided streamable HTTP endpoint and Bearer token. Once configured, you can invoke tools such as sync_generate_image, text_to_audio, and parse_video directly from Cursor.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"xskill ai": {
"xskill-ai": {
"type": "streamableHttp",
"url": "https://api.xskill.ai/api/v3/mcp-http",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
}McpServers
{
"xskill-ai": {
"type": "streamableHttp",
"url": "https://api.xskill.ai/api/v3/mcp-http",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}xSkill AI — MCP Server
AI content generation toolkit for Cursor. Generate images, videos, synthesize speech, clone voices, and more — all from your editor.Features
- 50+ AI Models — FLUX, Kling, Jimeng, Seedance 2.0, Seedream, Hailuo, Sora, Wan, and more - Image Generation — Text-to-image and image-to-image - Video Generation — Text-to-video, image-to-video, Seedance 2.0 Omni Reference - Text-to-Speech — Multiple voice models with speed/pitch control - Voice Cloning — Clone any voice from an audio sample - Voice Design — Create custom voices from natural language descriptions - Video Parsing — Extract watermark-free videos from Douyin, Kuaishou, Bilibili (free) - Sync Generation — Get instant image/video results without pollingAvailable Tools
| Tool | Description | |------|-------------| |list_models | List available AI models by category |
| get_model_info | Get model parameters and schema |
| submit_task | Submit async AI generation task |
| get_task | Check task status and results |
| sync_generate_image | Instant image generation |
| sync_generate_video | Instant video generation |
| text_to_audio | Text-to-speech synthesis |
| voice_clone | Clone voice from audio |
| parse_video | Extract watermark-free video URLs (free) |
| upload_image | Upload image to cloud storage (free) |
Setup
1. Get an API key at xskill.ai 2. Add to your.cursor/mcp.json:
``json
{
"mcpServers": {
"xskill-ai": {
"type": "streamableHttp",
"url": "https://api.xskill.ai/api/v3/mcp-http",
"headers": {
"Authorization": "Bearer sk-your-api-key"
}
}
}
}
`
Protocol
- Transport: Streamable HTTP
- Endpoint: https://api.xskill.ai/api/v3/mcp-http
- Auth: Bearer token or api_key` query parameter
License
MITSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
