skill-to-mcp and skill-mcp
About skill-to-mcp
biocontext-ai/skill-to-mcp
Convert AI Skills (Claude Skills format) to MCP server resources - Part of BioContextAI
Automatically discovers and exposes skills as MCP resources through three core tools: listing available skills, retrieving skill metadata and file contents, and accessing individual skill files with path traversal protection. The server parses YAML frontmatter from `SKILL.md` files to extract metadata, then recursively indexes skill directories for dynamic discovery. Integrates with any MCP client (Claude Desktop, Cline, etc.) via stdio transport and supports flexible deployment—local development, HTTP production servers, and Docker containers.
About skill-mcp
fkesheh/skill-mcp
LLM-managed skills platform using MCP - create, edit, and execute skills programmatically in Claude, Cursor, and any MCP-compatible client without manual file uploads.
# Technical Summary Provides a 22-module MCP server that enables LLMs to unify multiple skills in single code executions through cross-skill imports and automatic dependency/environment aggregation—achieving 98.7% token efficiency gains by following Anthropic's MCP code-execution pattern. Features CRUD operations for skill management stored in `~/.skill-mcp/skills/`, with support for Python/Bash script execution using PEP 723 inline dependencies and per-skill `.env` files. Architecture remains client-agnostic via standard MCP protocol, compatible with Claude Desktop, Cursor, claude.ai, and any MCP-compatible application without vendor lock-in.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work