SynClub MCP Server
Official SynClub Model Context Protocol (MCP) Server that enables powerful AI generation capabilities including text-to-speech, voice cloning, video generation, image generation, and more. Compatible with MCP clients like Claude Desktop, Cursor, Windsurf, and others.
Features
- Text-to-Speech: Convert text to natural speech with multiple voice options
- Voice Cloning: Clone voices from audio samples
- Video Generation: Generate videos from text prompts or images
- Image Generation: Create images from text descriptions
- Image Recognition: Analyze and understand image content
- Background Removal: Automatically remove backgrounds from images
- HD Image Restoration: Enhance image quality and resolution
- AI Search: Intelligent search with AI-powered results
- Japanese TTS: Specialized Japanese text-to-speech
Quick Start
1. Install uv (Python Package Manager)
curl -LsSf https://astral.sh/uv/install.sh | sh
powershell -c "irm https://astral.sh/uv/install.sh | iex"
2. Get Your API Key
Obtain your API key from your account information page on the SynClub server website.
3. Configure Your MCP Client
Claude Desktop
Step 1: find your config file
You can find your config file at:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
Or you can find your config file in claude setting:
Click claude setting:

Edit config file:

Open config file:

Step 2: append this config to your own file
{
"mcpServers": {
"SynClub": {
"command": "uvx",
"args": [
"synclub-mcp"
],
"env": {
"SYNCLUB_MCP_API": "your api key"
}
}
}
}
If you have any problem with the command uvx, try to use the command which uvx
to find the absolute path of uvx and replace the command in the config file.
step 3:save and restart your claude application
- important:make sure to restart claude that your config file will update and check the connection in claude developer
Available Tools
minimax_text_to_audio | Convert text to speech with customizable voice settings |
minimax_generate_video | Minimax generate videos |
minimax_voice_clone | Clone voices from audio files |
minimax_text_to_image | Generate images from text prompts |
kling_generate_text_to_video | Start generate videos from text descriptions using Kling models |
kling_query_ttv_task | Get the generate result from generate_text_to_video tool |
kling_generate_image_to_video | Start generate videos from images with text prompts using Kling models |
kling_query_gttv_task | Get the generate result from generate_image_to_video tool |
openai_image_recognition | Analyze and recognize image content |
gbu_remove_bg | Automatically remove image backgrounds |
gbu_hd_restore | Enhance image quality and resolution |
openai_generate_image | Generate images using alternative models |
gbu_ai_search | Perform AI-powered search queries |
gbu_japanese_tts | Japanese text-to-speech conversion |
gbu_generate_comic_story | Generate a comic story based on input story theme |
gbu_generate_comic_chapters | Generate comic story chapters based on novel input, character info and chapter number |
gbu_generate_comic_image_prompts | Generate image prompts based on comic story chapter and character info |
gbu_edit_comic_story | Edit comic story based on edit prompt and input story. |
gbu_edit_comic_chapters | Edit comic chapters based on edit prompt and input chapters. |
gbu_ugc_tti | Generate a anime character based on a text prompt |
gbu_anime_pose_align | Generate a pose align image based on an anime character image |
gbu_anime_comic_image | Generate a comic image based on prompt |
gbu_flux_edit_image | edit image based on image url and image prompts |
Environment Variables
SYNCLUB_MCP_API
: Your API key (required)
License
This project is licensed under the MIT License - see the LICENSE file for details.
From
https://github.com/520chatgpt01/Synclub-mcp-server