build-mcp-server

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a scaffolding and design guide for the Model Context Protocol (MCP) and does not contain any malicious behavior or instructions.
  • [EXTERNAL_DOWNLOADS]: Fetches templates and official tools from Cloudflare and the Model Context Protocol's public repositories using standard package managers (npm, pip).
  • [SAFE]: Explicitly instructs developers to handle sensitive credentials via environment variables and OS keychains, and warns against plain-text storage or sensitive data elicitation.
  • [COMMAND_EXECUTION]: Provides standard development commands and a shell script (scripts/test-server.sh) for initializing, deploying (via Cloudflare Wrangler), and smoke-testing servers using official CLI tools.
  • [SAFE]: Prompts are used for developer discovery phase (Phase 1) and do not attempt to bypass agent safety filters or override system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 09:56 PM