agentsclimarketplace

Skillsync mcp

Skill Glowboth/skillsync-mcp

Provide an MCP server that enables seamless integration and management of SkillsMP data with Node.js environments supporting Model Context Protocol.From the repository description

Install
npx -y skills add Glowboth/skillsync-mcp

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.4 KB, 338 tokens by cl100k_base, as published. Nobody here has run it

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

  • skillsmp_search — Search the SkillsMP marketplace by keyword
  • skillsmp_ai_search — AI-powered semantic search for skills
  • skillsmp_scan_skill — Security scan any GitHub skill repo
  • skillsmp_search_safe — Search + auto-scan top results in one step
  • skillsmp_install_skill — Scan, gate, and install a skill to ~/.claude/skills/
  • skillsmp_uninstall_skill — Remove an installed skill
  • skillsmp_list_installed — List installed skills with risk levels
  • skillsmp_audit_installed — Deep security audit of an installed skill

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.

What ships with it: 37 files

758.4 KB alongside SKILL.md, 18 of them executable

docs/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.