xSkill AI

Name: xSkill AI
Author: hexiaochun

@hexiaochun

代码仓库

关于 xSkill AI

AI content generation toolkit with 50+ models. Image/video generation, TTS, voice cloning, and more.

#ai #image-generation #video-generation #text-to-speech #voice-cloning #seedance #seedance-2-0 #flux #kling #sora #mcp

基本信息

分类

开发工具

传输方式

stdio

发布者

hexiaochun

提交者

SINGHO

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "xskill-ai": {
      "type": "streamableHttp",
      "url": "https://api.xskill.ai/api/v3/mcp-http",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

工具

List available AI models by category

Get model parameters and schema

Submit async AI generation task

Check task status and results

Instant image generation

Instant video generation

Text-to-speech synthesis

Clone voice from audio

Extract watermark-free video URLs (free)

Upload image to cloud storage (free)

概览

What is xSkill AI?

xSkill AI is an MCP server that provides a comprehensive AI content generation toolkit for Cursor. It integrates with the xSkill AI API to let users generate images, videos, and voice content directly from their editor. It is intended for developers and content creators who want to produce media assets programmatically.

How to use xSkill AI?

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.

Key features of xSkill AI

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

Use cases of xSkill AI

Generate images or videos from text prompts inside Cursor
Cloning a voice from an audio sample for narration
Designing custom voices using natural language descriptions
Extracting clean video URLs from Chinese social media platforms

FAQ from xSkill AI

What AI models does xSkill AI support?

It supports 50+ models including FLUX, Kling, Jimeng, Seedance 2.0, Seedream, Hailuo, Sora, Wan, and more. Use the list_models tool to see available categories.

What transport and authentication does xSkill AI use?

The server uses Streamable HTTP transport. Authentication is via a Bearer token in the Authorization header or by passing an api_key query parameter.

Is video parsing free?

Yes, the parse_video tool extracts watermark-free video URLs from Douyin, Kuaishou, and Bilibili at no charge.

Can I generate images and videos instantly?

Yes, sync_generate_image and sync_generate_video provide instant results without polling. Asynchronous task submission is also available via submit_task.