skillz
Verified Safeby mugoherick12-boop
Overview
Serve Anthropic-style skills to non-Claude clients via an MCP server.
Installation
skillzSecurity Notes
The server uses `yaml.safe_load` for parsing skill metadata, mitigating YAML-based code execution. Path traversal attempts for resources are explicitly checked and rejected. The server primarily serves skill instructions and resources; the execution of these skills/resources is offloaded to the client, meaning potential client-side risks if clients execute untrusted skill code. The server itself does not appear to execute arbitrary code from skills directly.
Similar Servers
claude-code-mcp
Provides an MCP server to allow LLMs to directly invoke Claude Code CLI for complex coding, file system, and Git operations, bypassing interactive permission prompts.
skillz
Acts as an MCP server to expose Claude-style skills and their resources as callable tools for AI agents.
Delphi-MCP-Server
Provides a Model Context Protocol (MCP) server implementation in Delphi to integrate AI agents like Claude Code with Delphi development workflows via an extensible tool and resource system.
consult-llm-mcp
Facilitates Claude Code to consult powerful external AI models for complex code analysis, debugging, and review tasks.