Atlas / MCP servers / jane-xiaoer / Skill Vision Control

Skill Vision ControlSAFE

mcp/jane-xiaoer/skill-vision-control

Safe MCP Skill version manager - detect updates, A/B testing, smart merge

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
9 6r · 3w · 0d
Transport
stdio
License
MIT
Stars
66
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://badge.fury.io/js/skill-vision-control) [](https://opensource.org/licenses/MIT)

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, 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

Version Control

Read from source at commit 3f32a979da05OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add skill-vision-control -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "skill-vision-control": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (9)

6 read · 3 write · 0 destructive.

ToolRiskDescription
svc_check_updatesreadCheck for available updates for skills
svc_download_updatewriteDownload a new version without replacing current
svc_get_conflictswriteGet merge conflicts for a skill
svc_get_skill_inforeadGet detailed information about a specific skill
svc_get_versionsreadGet all local versions of a skill
svc_list_skillsreadList all managed MCP skills
svc_mergewriteMerge official new version with custom changes
svc_rollbackreadRollback a skill to its previous version
svc_switch_versionreadSwitch to a specific version of a skill
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (2 observation(s))
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532
src/svc/cli.ts:609
console.log(`  GitHub Token: ${config.githubToken ? chalk.green('Set') : chalk.yellow('Not set')}`);
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, @types/tar, axios, chalk, commander, diff3, inquirer, node-cron
Why it matters. 21 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 3f32a979da05full audit observations/trust-audit/mcp-server/jane-xiaoer__skill-vision-control.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-073f32a979da05SAFEB89first audit
06

Questions

What is the Skill Vision Control MCP server?

Safe MCP Skill version manager - detect updates, A/B testing, smart merge

What tools does Skill Vision Control expose?

9 in total: 6 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Skill Vision Control safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Skill Vision Control need?

No credential environment variables were found in its source, so it appears to need none.

How does Skill Vision Control run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as skill-vision-control at 1.3.0.

How current is this page?

The grade is for one exact copy of the source (3f32a979da05), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement