K-Dense-AI/claude-skills-mcp

Overview

K-Dense-AI/claude-skills-mcp is a Python tool providing intelligent search capabilities to enable models and clients to use like native.

Capabilities

• • stdio transport support
• • network transport options
• • github integration
• • mcp client integration
• • workflow automation support

Best For

K-Dense-AI/claude-skills-mcp offers intelligent search capabilities for models and clients, facilitating native-like usage.

Decision Snapshot

• • GitHub stars: 374
• • Forks: 65
• • Source provenance count: 1
• • Active signal: Updated this week from lifecycle signals.
• • Last seen: 4/15/2026
• • Published: 3/17/2026

This is an MCP Find-authored example config generated from strong evidence.

Review official documentation and source metadata for complete setup parameters.

{
  "mcpServers": {
    "claude-skills-mcp": {
      "command": "uvx"
    }
  }
}

Usage

{ && "mcpServers": { && "claude-skills": { && "command": "uvx",

Features

• • **Two-Package Architecture**: Lightweight frontend (~15 MB) starts instantly; backend (~250 MB) downloads in background
• • **Semantic Search**: Vector embeddings for intelligent skill discovery
• • **Progressive Disclosure**: Multi-level skill loading (metadata → full content → files)
• • **Zero Configuration**: Works out of the box with curated skills
• • **Multi-Source**: Load from GitHub repositories and local directories
• • **Fast & Local**: No API keys needed, with automatic GitHub caching
• • **Configurable**: Customize sources, models, and content limits
• • **Architecture Guide** - Two-package design, data flow, and components

Use Cases

• • Supports capabilities such as: stdio transport support; network transport options; github integration.
• • Common usage themes: mcp, curated, markdown-list, awesome-mcp-servers-punkpeye.

Supported Clients / Integrations

• • stdio transport support
• • network transport options
• • github integration
• • mcp client integration
• • workflow automation support

Compatibility Signals

• • Claude Desktop: mentions (Mentioned in approved metadata/docs evidence.)
• • GitHub: supports (Detected in parser config/capability hints.)

Prompt Examples

Notes / Requirements

• • Primary language: Python
• • License: MIT
• • Documentation coverage: high
• • Parser coverage score: 1.00
• • Source feeds: Awesome MCP Servers (punkpeye)
• • Topic cluster: general

Official Links

• Website
• Repository
• Documentation 1 (/en/docs/claude-code/sk...)
• Documentation 2

Source Information

Related MCP Tools