Skill-to-MCP
Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, re
What is Skill-to-MCP?
Skill-to-MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to converts ai skills (following claude skills format) into mcp server resources, enabling llm applications to discover, access, and utilize self-contained skill directories through the model context pro...
Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, re
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Converts AI Skills (following Claude Skills format) into MCP
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx skill-to-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Skill-to-MCP
Skill-to-MCP is a Python server that converts AI skill directories (following the Claude Skills format, with a SKILL.md descriptor and associated files) into MCP resources that LLM applications can discover and use at runtime. It exposes three core tools — listing available skills, retrieving skill details and content, and reading individual skill files — enabling any MCP-compatible client to dynamically load and invoke self-contained skill packages. Developers building AI pipelines, biomedical tools, or Claude-powered workflows use it to manage and share reusable skill bundles without custom integration code.
Prerequisites
- Python 3.10+ installed
- uvx (from the uv package manager) or pip for installation
- A directory of Claude Skills format skill packages (each with a SKILL.md file)
- An MCP-compatible client such as Claude Desktop or Claude Code
Prepare your skills directory
Create a directory containing subdirectories for each skill. Each skill subdirectory must have a SKILL.md file that describes the skill's purpose, usage, and any associated files.
mkdir -p ~/my-skills/summarize
cat > ~/my-skills/summarize/SKILL.md << 'EOF'
# Summarize Skill
Summarizes documents into bullet points.
EOFInstall skill-to-mcp
Install using pip or use uvx to run directly without installing. The pip package name uses underscores: skill_to_mcp.
pip install --user skill_to_mcp
# or run directly with uvx (no install needed)
SKILLS_DIR=/path/to/skills uvx skill_to_mcpRun the server with your skills directory
Start the server pointing at your skills directory using the --skills-dir flag or the SKILLS_DIR environment variable.
skill_to_mcp --skills-dir ~/my-skills
# or via environment variable
SKILLS_DIR=~/my-skills uvx skill_to_mcpConfigure your MCP client
Add skill-to-mcp to your claude_desktop_config.json. The recommended approach uses uvx so no separate installation is needed.
Verify the three core tools are available
Once connected, your MCP client should have access to get_available_skills, get_skill_details, and get_skill_related_file tools. Ask Claude to list available skills to confirm the server is working.
Skill-to-MCP Examples
Client configuration
Claude Desktop configuration using uvx to run skill-to-mcp without a separate install step. Adjust the --skills-dir path to your actual skills directory.
{
"mcpServers": {
"skill-to-mcp": {
"command": "uvx",
"args": [
"skill_to_mcp",
"--skills-dir",
"/Users/yourname/my-skills"
],
"env": {
"UV_PYTHON": "3.12"
}
}
}
}Prompts to try
Natural language prompts to discover and use skills through Claude once skill-to-mcp is connected.
- "What skills are available in my skills directory?"
- "Show me the details and description for the summarize skill"
- "Read the prompt.txt file from the data-extraction skill"
- "List all files included in the biomedical-ner skill"
- "Use the summarize skill to condense this document"Troubleshooting Skill-to-MCP
get_available_skills returns an empty list
Verify that SKILLS_DIR or --skills-dir points to the correct directory and that each skill subdirectory contains a SKILL.md file. The server only recognizes skill directories that have this descriptor file present.
get_skill_related_file is blocked with a path validation error
The server enforces that file reads stay within the skill's own directory for security. Ensure you are only requesting files that exist inside the specific skill subdirectory, not parent directories or absolute paths outside it.
Server fails to start with uvx giving Python version errors
Set UV_PYTHON to a supported Python version (e.g., '3.12') in the env block of your MCP config, or ensure the system Python is 3.10 or higher before running uvx.
Frequently Asked Questions about Skill-to-MCP
What is Skill-to-MCP?
Skill-to-MCP is a Model Context Protocol (MCP) server that converts ai skills (following claude skills format) into mcp server resources, enabling llm applications to discover, access, and utilize self-contained skill directories through the model context protocol. provides tools to list available skills, re It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Skill-to-MCP?
Follow the installation instructions on the Skill-to-MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Skill-to-MCP?
Skill-to-MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Skill-to-MCP free to use?
Yes, Skill-to-MCP is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Skill-to-MCP Alternatives — Similar Coding Agents Servers
Looking for alternatives to Skill-to-MCP? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Skill-to-MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Skill-to-MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.