Skill Vision Control (SVC)
A version management server for MCP skills that enables automated update detection, parallel version testing, and smart merging of custom modifications with official updates. It allows users to safely switch, rollback, and manage local skill versions through a standardized suite of MCP tools.
README
Skill Vision Control (SVC)
Safe MCP Skill Version Manager - Detect updates, parallel testing, smart merge, confirm before replace
Features
- 🔍 Update Detection - Automatically detect new versions from GitHub/npm
- 📦 Version Management - Keep multiple versions, switch anytime
- 🔀 Smart Merge - Merge official updates with your custom changes
- 🧪 A/B Testing - Test new versions before switching
- ⏰ Scheduled Checks - Automatic weekly/monthly update checks
- 🔔 Notifications - Desktop notifications for updates
- 🤖 MCP Server - Let AI manage your skills
Installation
npm install -g skill-vision-control
Or with yarn:
yarn global add skill-vision-control
Quick Start
# Add a skill to manage
svc add weather --source github:username/weather-mcp
# Check for updates
svc check
# Download new version (keeps old version)
svc download weather
# Test and switch
svc switch weather --version v1.1.0
# Or if you have custom changes, merge them
svc merge weather
Commands
Skill Management
| Command | Description |
|---|---|
svc add <name> --source <url> |
Register a skill (github:user/repo or npm:package) |
svc list |
List all managed skills |
svc info <name> |
Show detailed information |
svc remove <name> |
Remove a skill |
Version Control
| Command | Description |
|---|---|
svc check [name] |
Check for updates |
svc download <name> |
Download new version (keep old) |
svc versions <name> |
List all local versions |
svc switch <name> -v <version> |
Switch to specific version |
svc rollback <name> |
Rollback to previous version |
svc confirm <name> |
Confirm current version |
svc cleanup <name> --keep <n> |
Clean old versions |
Custom Modifications
| Command | Description |
|---|---|
svc fork <name> |
Create custom branch for modifications |
svc save <name> -c "comment" |
Save your modifications |
svc diff <name> |
View differences from official |
svc merge <name> |
Merge official update with your changes |
svc conflicts <name> |
View merge conflicts |
svc resolve <name> -f <file> -u <choice> |
Resolve conflicts |
Schedule
| Command | Description |
|---|---|
svc schedule set -i <days> |
Set check interval (1/7/14/30 days) |
svc schedule show |
Show current schedule |
svc schedule enable |
Enable scheduled checks |
svc schedule disable |
Disable scheduled checks |
svc schedule run |
Manually trigger check |
Workflow Examples
Basic Update Flow
# 1. Check for updates
svc check
# Output: weather: v1.0.0 → v1.1.0 available
# 2. Download (old version preserved)
svc download weather
# 3. Test new version
svc switch weather -v v1.1.0 -t official
# 4. If good, confirm; if not, rollback
svc confirm weather
# or
svc rollback weather
Custom Changes + Update
# 1. Create custom branch
svc fork weather
# 2. Make your modifications...
# 3. Save changes
svc save weather -c "Added Chinese language support"
# 4. Later, when update available
svc check
# Output: ⚠️ You have custom changes. Use "svc merge"
# 5. Download and merge
svc download weather
svc merge weather
# 6. If conflicts exist
svc conflicts weather
svc resolve weather -f src/config.ts -u custom
# 7. Test merged version
svc switch weather -v v1.1.0-merged -t merged
# 8. Confirm
svc confirm weather
Using as MCP Server
Add to your MCP configuration:
{
"mcpServers": {
"skill-vision-control": {
"command": "svc",
"args": ["serve"]
}
}
}
Available MCP tools:
svc_list_skills- List all managed skillssvc_get_skill_info- Get skill detailssvc_check_updates- Check for updatessvc_get_versions- Get local versionssvc_switch_version- Switch versionsvc_rollback- Rollback to previoussvc_download_update- Download new versionsvc_merge- Merge with custom changessvc_get_conflicts- View merge conflicts
Data Storage
All data is stored in ~/.svc/:
~/.svc/
├── skills.json # Skill registry
├── schedule.json # Schedule settings
├── config.json # Global config
└── versions/ # Version storage
└── <skill>/
├── official/
├── custom/
├── merged/
└── active -> ...
Configuration
Supported Sources
- GitHub:
github:username/repoorusername/repo - npm:
npm:package-name
Schedule Options
1d- Daily checks7d- Weekly checks (default)14d- Bi-weekly checks30d- Monthly checks
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see LICENSE for details.
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。