Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1
Prepare the server locally
Run this once before adding it to Claude Code.
uv pip install mcp-skill-server2
Register it in Claude Code
claude mcp add mcp-skill-server -- uvx mcp-skill-server serve /path/to/my/skillsReplace any placeholder paths in the command with the real path on your machine.
Available Tools (3)
Once configured, MCP Skill Server gives your AI agent access to:
list_skillsLists all available skills in the configured directory.get_skillRetrieves details and metadata for a specific skill.skill_namerun_skillExecutes a specific skill using its defined entry point.skill_nameargumentsTry It Out
After setup, try these prompts with your AI agent:
→List all the skills currently available in my skills directory.
→Run the 'data-processor' skill with the input file set to 'report.csv'.
→Get the documentation and parameter requirements for the 'image-optimizer' skill.
→Help me scaffold a new skill using the skill init command.
Prerequisites & system requirements
- An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
- Python 3.8+ with pip installed
Alternative installation methods
Claude Code
claude mcp add skills -- uvx mcp-skill-server serve /path/to/my/skillsManual (PyPI)
uv pip install mcp-skill-serverConare · memory for coding agents
Keep this setup from going cold
Save the docs, env vars, and workflow around MCP Skill Server in Conare so Claude Code, Codex, and Cursor remember it next time.
Remember this setup$npx conare@latest