Skill To MCP

v1.0.0Coding Agentsstable

Convert AI Skills (Claude Skills format) to MCP server resources - Part of BioContextAI

aibiocontextbiomedicalclaudefastmcp
Share:
25
Stars
0
Downloads
0
Weekly
0/5

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 convert ai skills (claude skills format) to mcp server resources - part of biocontextai

Convert AI Skills (Claude Skills format) to MCP server resources - Part of BioContextAI

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Convert AI Skills (Claude Skills format) to MCP server resou

Use Cases

Claude Skills MCP conversion
Biomedical skill integration
FastMCP resource management
biocontext-ai

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx skill-to

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Skill To MCP

skill-to-mcp is a Python-based MCP server that converts Claude AI Skills — structured skill definitions stored as SKILL.md files in a directory — into MCP server resources that any MCP-compatible client can discover and invoke. Part of the BioContextAI project, it is primarily designed for biomedical workflows but works with any skills collection. It exposes three tools for listing available skills, retrieving full skill definitions, and reading skill-related files, enabling AI agents to dynamically discover and execute structured capability bundles.

Prerequisites

  • Python 3.12+ and uv package manager installed
  • A directory containing skill definitions in SKILL.md format
  • An MCP-compatible client such as Claude Desktop
  • Optional: pip for alternative installation without uv
1

Prepare a skills directory

Create a directory where each subdirectory represents a skill, containing at minimum a SKILL.md file describing the skill's purpose, parameters, and behavior. This directory path is passed to the server at startup.

mkdir -p ~/my-skills/data-analysis
cat > ~/my-skills/data-analysis/SKILL.md << 'EOF'
# Data Analysis Skill
Description: Analyzes tabular data using pandas
EOF
2

Install skill_to_mcp

Install the package via pip or use uvx for a no-install run. The PyPI package name uses underscores: skill_to_mcp.

pip install skill_to_mcp
# or run without installing:
uvx skill_to_mcp --skills-dir /path/to/skills
3

Configure the MCP client with the skills directory

Add the server to claude_desktop_config.json, passing the path to your skills directory via the --skills-dir argument. You can run multiple instances pointing to different skill collections.

{
  "mcpServers": {
    "biomedical-skills": {
      "command": "uvx",
      "args": ["skill_to_mcp", "--skills-dir", "/path/to/skills"],
      "env": {
        "UV_PYTHON": "3.12"
      }
    }
  }
}
4

Restart your MCP client and verify skill discovery

Restart Claude Desktop. Ask Claude to list available skills — it will call the get_available_skills tool and return the names, descriptions, and paths of all skills found in the configured directory.

Skill To MCP Examples

Client configuration

Claude Desktop configuration using uvx to run skill_to_mcp with a specified skills directory and Python version.

{
  "mcpServers": {
    "biomedical-skills": {
      "command": "uvx",
      "args": ["skill_to_mcp", "--skills-dir", "/Users/me/skills"],
      "env": {
        "UV_PYTHON": "3.12"
      }
    }
  }
}

Prompts to try

Queries that use the get_available_skills, get_skill_details, and get_skill_related_file tools to discover and load skill definitions.

- "List all available skills in my skills directory"
- "Show me the full details and file list for the 'data-analysis' skill"
- "Read the config.json file inside the 'protein-folding' skill directory"
- "Which skills are available for biomedical data processing?"
- "Get the SKILL.md content for the 'gene-expression' skill"

Troubleshooting Skill To MCP

get_available_skills returns an empty list

Verify that the --skills-dir path exists and contains subdirectories with SKILL.md files. Each skill must be a directory (not a flat file) containing SKILL.md. Run 'ls /path/to/skills' to confirm the structure.

uvx skill_to_mcp fails with 'package not found'

Ensure uv is installed ('pip install uv' or via https://astral.sh/uv). The package name uses underscores: skill_to_mcp, not skill-to-mcp. Try 'pip install skill_to_mcp' as an alternative if uvx continues to fail.

get_skill_related_file refuses to read a file with a path traversal error

The tool includes directory traversal protection — it only reads files inside the specific skill's directory. Paths like '../other-skill/file.txt' are blocked by design. Always request files relative to the skill's own directory.

Frequently Asked Questions about Skill To MCP

What is Skill To MCP?

Skill To MCP is a Model Context Protocol (MCP) server that convert ai skills (claude skills format) to mcp server resources - part of biocontextai 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.

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.

Quick Config Preview

{ "mcpServers": { "skill-to": { "command": "npx", "args": ["-y", "skill-to"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

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.

33,000+ ServersFree & Open SourceStep-by-Step Guides