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 skill-mcp-server2
Register it in Claude Code
claude mcp add skill-mcp -- uvx skill-mcp-server --skills-dir /path/to/your/skills --workspace /path/to/workspaceReplace any placeholder paths in the command with the real path on your machine.
Available Tools (5)
Once configured, Skill MCP Server gives your AI agent access to:
list_skillsList all available skillsskillLoad a specific skill to get detailed instructions from its SKILL.mdskill_nameskill_resourceRead reference documents or templates from skill packagesskill_nameresource_pathskill_scriptExecute scripts bundled with skills in a secure environmentskill_namescript_namefile_readRead files from the specified workspacefile_pathTry It Out
After setup, try these prompts with your AI agent:
→List all the skills currently available in my skills directory.
→Load the instructions for the 'data-analysis' skill.
→Execute the 'process_data.py' script from the 'data-analysis' skill package.
→Read the output report generated in my workspace folder.
Prerequisites & system requirements
- An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
- Python 3.8+ with pip installed
Alternative installation methods
pip
pip install skill-mcp-serverConare · memory for coding agents
Keep this setup from going cold
Save the docs, env vars, and workflow around Skill MCP Server in Conare so Claude Code, Codex, and Cursor remember it next time.
Remember this setup$npx conare@latest