Skill-vision-control: Secure MCP Skill Version Management Tool with Auto-update, Scan & Multi-version Support

Skill Vision Control

A secure MCP skill version manager that supports automatic update detection, security scanning, multi-version management, intelligent merging, and A/B testing.

Developer tools Version control #Version management #Security scanning #Intelligent merging #Skill update .TypeScript

rating : 2.5 points

downloads : 0

update time : 2026-03-12

Open Site

What is Skill Vision Control?

Skill Vision Control (SVC) is an intelligent version management system specifically designed for MCP (Model Context Protocol) skills. It's like a'skill butler' that helps you securely manage, update, and test various AI skills, ensuring you always use the most stable and secure versions. Imagine you have many AI assistant skills, such as weather queries, translation, and code generation. SVC will automatically check if there are new versions of these skills, conduct security checks before downloading, allow you to test the new version before deciding whether to replace it, and preserve your personalized modifications.

How to use SVC?

Using SVC is very simple and mainly involves command-line operations. You only need a few basic commands to get started: 1. Add skills to be managed (from GitHub or npm) 2. Regularly check for updates 3. Download new versions for testing 4. Confirm to use or roll back to the old version SVC also provides an MCP server mode, allowing AI assistants to help you manage skills and achieve automated management.

Applicable scenarios

SVC is particularly suitable for the following scenarios: - You use multiple MCP skills and need unified management - You have made personalized modifications to some skills but also want to get official updates - You care about the security of skills and hope to conduct automatic checks before updates - You want to test new versions without affecting current use - You hope that AI assistants can help you manage skill updates

Main features

Automatic update detection

Automatically check if there are new versions of skills from GitHub and npm, and support scheduled checks

Security scanning

Automatically scan the code security before downloading, detect potential risks, and protect your system security

Multi-version management

Retain multiple versions simultaneously, switch at any time, and support rolling back to any historical version

Intelligent merging

Automatically merge official updates with your personalized modifications, making it more convenient to resolve conflicts

A/B testing

Test new versions without affecting the production environment to ensure stability

Scheduled checks

Set the frequency of automatic checks (daily/weekly/monthly) to not miss important updates

MCP server integration

Run as an MCP server, allowing AI assistants to manage your skills

Desktop notifications

Send desktop notifications when there are new versions to remind you to update in time

Advantages

🛡️ Security first: Conduct security scans for each download to prevent malicious code

🔄 Risk-free updates: Test before switching and roll back at any time if there are problems

🎨 Personalization preservation: Intelligent merging allows you to update while retaining custom modifications

🤖 Automated management: Support scheduled checks and AI assistant management, saving time and effort

📊 Clear version history: All version histories are clearly visible, making management easier

Limitations

📚 Learning curve: You need to learn some command-line operations

💾 Storage space: Retaining multiple versions will occupy more disk space

🔗 Network dependency: You need a network connection to check for updates and download

⚙️ Configuration requirements: You need basic knowledge of command-line usage

How to use

Install SVC

First, you need to install the SVC tool on your computer

Add skills

Add the MCP skills you want to manage to SVC

Check for updates

Regularly check if there are new versions of the skills you manage

Download and test

Download the new version for testing, and the old version will be retained

Switch versions

Switch to the new version after satisfactory testing. You can roll back if you are not satisfied

Usage examples

Example 1: Securely update the weather query skill

You are using a weather query MCP skill and find that a new version has been released. You want to update but are worried about security.

Example 2: Preserve personalized modifications of the translation skill

You have made personalized modifications to a translation skill (such as adding professional terms), and now the official has released a new version.

Example 3: Batch manage multiple skills

You are using 10 different MCP skills and want to manage their updates uniformly.

Example 4: Let AI assistants manage skills

You hope that AI assistants can help you manage skill updates and achieve automation.

Frequently Asked Questions

Which sources of skills does SVC support?

What content will the security scan check?

If I don't like the new version, how can I roll back?

Will SVC occupy a lot of disk space?

How can I make SVC automatically check for updates?

Can I use SVC without an internet connection?

What should I do if there are conflicts during merging?

Related resources

GitHub repository

The source code and latest version of SVC

npm package page

View and install SVC on npm

MCP protocol documentation

Understand the detailed specifications of the Model Context Protocol

Sentinel security scan

The security scanning tool integrated with SVC

🚀 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.
🛡️ Security Scanning: Auto scan before download (Sentinel integration).
📦 Version Management: Keep multiple versions and 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

You can install skill-vision-control using either npm or yarn:

Using npm

npm install -g skill-vision-control

Using yarn

yarn global add skill-vision-control

🚀 Quick Start

Here are some basic commands to get you started with SVC:

# 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

💻 Usage 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

Security Audit Before Install

# Scan a skill before installing
svc scan ~/Downloads/some-mcp-skill

# Output:
# 🛡️  Sentinel Security Scan Report
# ══════════════════════════════════════════════════
# Risk Level: MEDIUM
# Recommendation: REVIEW
# 
# ⚠️  SUSPICIOUS: 3 items found
#    - src/api.ts:15 - Network request (axios)
#    - src/config.ts:8 - Environment variable access

# Audit all installed skills
svc audit

# Audit specific skill with details
svc audit weather -v

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

📚 Documentation

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

Security Scanning

Command	Description
`svc scan <path>`	Scan any skill directory for security issues
`svc audit [name]`	Audit installed skill(s)
`svc download <name> --skip-security`	Download without security scan (not recommended)

Using as MCP Server

Add the following configuration to your MCP configuration file:

{
  "mcpServers": {
    "skill-vision-control": {
      "command": "svc",
      "args": ["serve"]
    }
  }
}

Available MCP tools:

svc_list_skills - List all managed skills
svc_get_skill_info - Get skill details
svc_check_updates - Check for updates
svc_get_versions - Get local versions
svc_switch_version - Switch version
svc_rollback - Rollback to previous
svc_download_update - Download new version
svc_merge - Merge with custom changes
svc_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 -> ...

Security Scanning

SVC integrates Sentinel security patterns for automatic code scanning.

Detection Capabilities

Level	Description	Examples
CRITICAL	High-risk patterns	`eval()`, `exec()`, `rm -rf`, registry access
SUSPICIOUS	Needs review	Network requests, env vars, file operations
WARNING	Potential issues	Long lines, high entropy files

Risk Levels

Level	Action
`SAFE`	Safe to install
`LOW`	Minor concerns, review recommended
`MEDIUM`	Review required before install
`HIGH`	Significant risks detected
`CRITICAL`	Do not install without careful review

Auto-Scan on Download

When you run svc download, a security scan runs automatically:

svc download weather
# 🛡️  Running security scan...
# ✅ Security scan passed
# ✓ Download complete

If issues are found:

svc download untrusted-skill
# 🛡️  Running security scan...
# 🛑 Security scan found critical issues!
# ? Do you still want to proceed? (NOT RECOMMENDED) (y/N)

To skip the security scan (not recommended):