mcp-builder

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation and SDK specifications from official Model Context Protocol domains and GitHub organizations. This ensures the agent has access to the most current protocol standards during the development process.
  • [COMMAND_EXECUTION]: The evaluation script (scripts/evaluation.py) is designed to launch and test MCP servers by executing commands and arguments specified by the user. This functionality is central to its purpose as a development and testing tool.
  • [SAFE]: Sensitive information such as API keys is managed through environment variables rather than hardcoding, adhering to secure development standards.
  • [SAFE]: The instructions include operational safety guidance, such as using command timeouts and process managers to handle the long-running nature of MCP server processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:17 AM