install
source · Clone the upstream repo
git clone https://github.com/adityasugandhi/skillsync-mcp
Claude Code · Install into ~/.claude/skills/
git clone --depth=1 https://github.com/adityasugandhi/skillsync-mcp ~/.claude/skills/adityasugandhi-skillsync-mcp-skillsync-mcp
manifest:
SKILL.mdsource content
SkillSync MCP — Security-Gated Skill Manager
Search, scan, install, and manage Claude Code skills with built-in security scanning. Every installation is gated behind a 60+ pattern threat scan.
Tools
— Search the SkillsMP marketplace by keywordskillsmp_search
— AI-powered semantic search for skillsskillsmp_ai_search
— Security scan any GitHub skill reposkillsmp_scan_skill
— Search + auto-scan top results in one stepskillsmp_search_safe
— Scan, gate, and install a skill toskillsmp_install_skill~/.claude/skills/
— Remove an installed skillskillsmp_uninstall_skill
— List installed skills with risk levelsskillsmp_list_installed
— Deep security audit of an installed skillskillsmp_audit_installed
Setup
Add to your MCP client config:
{ "mcpServers": { "skillsmp": { "command": "npx", "args": ["-y", "@stranzwersweb2/skillsync-mcp"] } } }
When to Use
- User asks to find, search, or browse skills
- User wants to install a skill from GitHub
- User wants to check if a skill is safe before installing
- User wants to see what skills are installed or audit them
- User mentions SkillsMP marketplace
Security
Critical threats (prompt injection, RCE, credential theft) permanently block installation. Medium/high risk requires explicit
force: true. All output is sanitized against prompt injection.