mcp-builder
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation and SDK READMEs from official repositories (modelcontextprotocol.io and github.com/modelcontextprotocol) to provide the agent with the latest protocol specifications.
- [COMMAND_EXECUTION]: The evaluation script launches local MCP servers as subprocesses using user-provided commands (e.g., 'python server.py') to test tool functionality.
- [SAFE]: All identified behaviors, including external documentation fetching and subprocess management, are necessary for the skill's primary purpose as a developer tool and show no signs of malicious intent or unauthorized data access.
Audit Metadata