Skip to main content
Glama

mcp-skills

by bobmatnyc
OverviewInspectNewSchemaRelated ServersScore
Python
Local
MIT License

mcp-skills

Dynamic RAG-powered skills for code assistants via Model Context Protocol (MCP)

mcp-skills is a standalone Python application that provides intelligent, context-aware skills to code assistants through hybrid RAG (vector + knowledge graph). Unlike static skills that load at startup, mcp-skills enables runtime skill discovery, automatic recommendations based on your project's toolchain, and dynamic loading optimized for your workflow.

Key Features

  • 🚀 Zero Config: mcp-skills setup handles everything automatically

  • 🧠 Intelligent: Auto-detects your project's toolchain (Python, TypeScript, Rust, Go, etc.)

  • 🔍 Dynamic Discovery: Vector similarity + knowledge graph for better skill finding

  • 📦 Multi-Source: Pulls skills from multiple git repositories

  • ⚡ On-Demand Loading: Skills loaded when needed, not all at startup

  • 🔌 MCP Native: First-class Model Context Protocol integration

Installation

From PyPI

pip install mcp-skills

From Source

git clone https://github.com/yourusername/mcp-skills.git cd mcp-skills pip install -e .

Quick Start

1. Setup

Run the interactive setup wizard to configure mcp-skills for your project:

mcp-skills setup

This will:

  • Detect your project's toolchain

  • Clone relevant skill repositories

  • Build vector + knowledge graph indices

  • Configure MCP server integration

  • Validate the setup

2. Start the MCP Server

mcp-skills serve

The server will start and expose skills to your code assistant via MCP protocol.

3. Use with Claude Code

Skills are automatically available in Claude Code. Try:

  • "What testing skills are available for Python?"

  • "Show me debugging skills"

  • "Recommend skills for my project"

Project Structure

~/.mcp-skills/ ├── config.yaml # User configuration ├── repos/ # Cloned skill repositories │ ├── anthropics/skills/ │ ├── obra/superpowers/ │ └── custom-repo/ ├── indices/ # Vector + KG indices │ ├── vector_store/ │ └── knowledge_graph/ └── metadata.db # SQLite metadata

Architecture

mcp-skills uses a hybrid RAG approach combining:

Vector Store (ChromaDB/Qdrant):

  • Fast semantic search over skill descriptions

  • Embeddings generated with sentence-transformers

Knowledge Graph (NetworkX):

  • Skill relationships and dependencies

  • Category and toolchain associations

  • Related skill discovery

Toolchain Detection:

  • Automatic detection of programming languages

  • Framework and build tool identification

  • Intelligent skill recommendations

Configuration

Global Configuration (~/.mcp-skills/config.yaml)

repositories: - url: https://github.com/anthropics/skills.git priority: 100 auto_update: true vector_store: backend: chromadb embedding_model: all-MiniLM-L6-v2 server: transport: stdio log_level: info

Project Configuration (.mcp-skills.yaml)

project: name: my-project toolchain: primary: Python frameworks: [Flask, SQLAlchemy] auto_load: - systematic-debugging - test-driven-development

CLI Commands

# Setup and Configuration mcp-skills setup # Interactive setup wizard mcp-skills config # Show configuration # Server mcp-skills serve # Start MCP server (stdio) mcp-skills serve --http # Start HTTP server mcp-skills serve --dev # Development mode (auto-reload) # Skills Management mcp-skills search "testing" # Search skills mcp-skills list # List all skills mcp-skills info pytest-skill # Show skill details mcp-skills recommend # Get recommendations # Repositories mcp-skills repo add <url> # Add repository mcp-skills repo list # List repositories mcp-skills repo update # Update all repositories # Indexing mcp-skills index # Rebuild indices mcp-skills index --incremental # Index only new skills # Utilities mcp-skills health # Health check mcp-skills stats # Usage statistics

MCP Tools

mcp-skills exposes these tools to code assistants:

  • search_skills: Natural language skill search

  • get_skill: Load full skill instructions by ID

  • recommend_skills: Get recommendations for current project

  • list_categories: List all skill categories

  • update_repositories: Pull latest skills from git

Development

Requirements

  • Python 3.11+

  • Git

Setup Development Environment

git clone https://github.com/yourusername/mcp-skills.git cd mcp-skills pip install -e ".[dev]"

Run Tests

make quality

Linting and Formatting

make lint-fix

Documentation

Architecture

See docs/architecture/README.md for detailed architecture design.

Skills Collections

See docs/skills/RESOURCES.md for a comprehensive index of skill repositories compatible with mcp-skills, including:

  • Official Anthropic skills

  • Community collections (obra/superpowers, claude-mpm-skills, etc.)

  • Toolchain-specific skills (Python, TypeScript, Rust, Go, Java)

  • Operations & DevOps skills

  • MCP servers that provide skill-like capabilities

Contributing

Contributions welcome! Please read our contributing guidelines first.

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Run make quality to ensure tests pass

  5. Submit a pull request

License

MIT License - see LICENSE for details.

Acknowledgments

Links

Status: 🚧 Early development - MVP in progress

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

Related Resources

New MCP Servers

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bobmatnyc/mcp-skills'

If you have feedback or need assistance with the MCP directory API, please join our Discord server