The Agent Skills Directory

[SAFE]: The skill and its associated scripts do not contain any malicious patterns, obfuscation, or unauthorized data access techniques. All behaviors are consistent with its stated purpose as a developer toolset.- [COMMAND_EXECUTION]: The scripts/evaluation.py and scripts/connections.py scripts provide the capability to execute local commands (e.g., python server.py) to launch and test MCP servers via the stdio transport. This is a core functionality for local development and is fully controlled by the user via command-line arguments.- [EXTERNAL_DOWNLOADS]: The skill instructions include steps to fetch documentation from the official Model Context Protocol website (modelcontextprotocol.io) and its official GitHub repositories (github.com/modelcontextprotocol). These are well-known, trusted sources for the technology being documented and do not involve the execution of untrusted remote code.

mcp-builder