接入你的智能体
从发布者处安装。不是 PlugMCP 端点。
远程 URL 还是本机命令? 两种安装方式的区别
An MCP (Model Context Protocol) server for SkillsMP -- the marketplace for Claude Code skills. Search, scan for security threats, install, and manage skills directly from your AI assistant.
The only tool that gates skill installation behind a full security scan.
~/.claude/skills/ with automatic security gatefs.watch for live syncWorks with Claude Code | OpenClaw | Cursor | Windsurf | GitHub Copilot | Zed | nanobot -- any MCP-compatible client
Install via Smithery for automatic configuration with any supported client.
Add to ~/.claude/settings.json:
{
"mcpServers": {
"skillsmp": {
"command": "npx",
"args": ["-y", "@stranzwersweb2/skillsync-mcp"]
}
}
}
Add to ~/.openclaw/mcp.json:
{
"mcpServers": {
"skillsmp": {
"version": "1.3.0",
"autoUpdate": false,
"command": "npx",
"args": ["-y", "@stranzwersweb2/[email protected]"]
}
}
}
OpenClaw uses the same
SKILL.mdformat as Claude Code. Skills installed via this server are compatible with both platforms. OpenClaw users should pin versions and review tool policies per the security hardening guide.
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"skillsmp": {
"command": "npx",
"args": ["-y", "@stranzwersweb2/skillsync-mcp"]
}
}
}
Add to ~/.windsurf/mcp.json:
{
"mcpServers": {
"skillsmp": {
"command": "npx",
"args": ["-y", "@stranzwersweb2/skillsync-mcp"]
}
}
}
Add to .github/copilot-mcp.json in your project root, or ~/.github/copilot-mcp.json for global config:
{
"mcpServers": {
"skillsync": {
"command": "npx",
"args": ["-y", "@stranzwersweb2/skillsync-mcp"],
"env": {
"SKILLSMP_API_KEY": "your-api-key"
}
}
}
}
Add to ~/.config/zed/settings.json under the "context_servers" key:
{
"context_servers": {
"skillsync": {
"command": {
"path": "npx",
"args": ["-y", "@stranzwersweb2/skillsync-mcp"],
"env": {
"SKILLSMP_API_KEY": "your-api-key"
}
}
}
}
}
npm install -g @stranzwersweb2/skillsync-mcp
Then reference in any MCP config:
{
"mcpServers": {
"skillsmp": {
"command": "skillsync-mcp"
}
}
}
Installation is gated by a multi-level security scan:
github.com URLs acceptednpm install --ignore-scripts -- blocks postinstall attacksSearch SkillsMP -> Pick a skill -> Security scan (60+ patterns)
|
Critical? -> BLOCKED
Medium/High? -> Requires force=true
Safe/Low? -> Download from GitHub
|
Write to ~/.claude/skills/<name>/
|
npm install --ignore-scripts (if needed)
|
Startup verification (fs.watch + content hash)
|
Restart your MCP client to load
Ask your AI assistant:
Search for git-related skills on SkillsMP
Scan this skill for security issues: https://github.com/user/repo/tree/main/skills/my-skill
Install the commit skill from https://github.com/user/repo/tree/main/skills/commit
List all my installed skills
Run a deep security audit on the commit skill
Uninstall the commit skill
git clone https://github.com/adityasugandhi/skillsync-mcp.git
cd skillsync-mcp
npm install
npm run build
npm run dev # Watch mode with tsx
npm run test:build # Build + run tests
Contributions are welcome. Please see CONTRIBUTING.md for guidelines.
good-first-issue labelnpm run test:build)The npm package is published under the legacy scope @stranzwersweb2 — this is the same author as the GitHub owner adityasugandhi. Both identities belong to Aditya Sugandhi.
Aditya Sugandhi -- adityasugandhi.com | GitHub
SkillSync MCP — security-gated skill management for Claude Code, OpenClaw, Cursor & Windsurf. 60+ threat pattern scanner.
工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
Skillsync 通过 stdio 在本地运行。
上次检查时间:2026-10-27。 SkillSync MCP — security-gated skill management for Claude Code, OpenClaw, Cursor & Windsurf. 60+ threat pattern scanner.