skillsh-mcp
MCP server for searching and managing AI agent skills from skills.sh, including search, popular skills, details, and install commands.
README
MCP Server for skills.sh
MCP (Model Context Protocol) server for searching and managing AI agent skills from skills.sh.
Features
- 🔍 Search Skills: Search for skills by query term
- 📊 Popular Skills: Get top popular skills from leaderboard
- 📝 Skill Details: Get information about specific skills
- 💻 Install Commands: Generate install commands for skills
Installation
1. Build the server
cd skillsh-mcp
npm install
npm run build
2. Configure your client
For Claude Code
Option A: Using claude mcp add (recommended)
claude mcp add skills-sh --scope user -- node /absolute/path/to/skillsh-mcp/dist/index.js
Scopes available:
--scope local(default) — Available only to you in the current project--scope project— Shared via.mcp.jsonin the project root (committed to git)--scope user— Available globally across all your projects
Option B: Using .mcp.json file
Create or edit .mcp.json in your project root:
{
"mcpServers": {
"skills-sh": {
"command": "node",
"args": ["/absolute/path/to/skillsh-mcp/dist/index.js"],
"env": {}
}
}
}
Option C: Using claude mcp add-json
claude mcp add-json skills-sh '{"command":"node","args":["/absolute/path/to/skillsh-mcp/dist/index.js"]}'
For Cursor
Add to .cursor/mcp.json in your workspace:
{
"mcpServers": {
"skills-sh": {
"command": "node",
"args": ["${workspaceFolder}/skillsh-mcp/dist/index.js"]
}
}
}
Then restart Cursor.
Usage
The server provides the following tools:
search_skills
Search for skills on skills.sh
- query (required): Search term (e.g., "mapbox", "react", "gis")
- limit (optional): Maximum number of results (default: 50)
get_popular_skills
Get popular skills from the leaderboard
- limit (optional): Number of results (default: 20)
- timeframe (optional): "all", "trending", or "hot" (default: "all")
get_skill_details
Get detailed information about a specific skill
- owner (required): GitHub owner/username
- repo (required): Repository name
- skillId (required): Skill ID
get_install_command
Get the npx install command for a skill
- owner (required): GitHub owner/username
- repo (required): Repository name
Development
# Install dependencies
npm install
# Build
npm run build
# Run in development mode
npm run dev
Compatibility
| Client | Transport | Status |
|---|---|---|
| Claude Code | stdio | ✅ Supported |
| Cursor | stdio | ✅ Supported |
| Claude Desktop | stdio | ✅ Supported |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.