mcp-server-dev

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation instructs developers to install official MCP packages and standard development tools.
  • Evidence: References to @modelcontextprotocol/server, @modelcontextprotocol/node, @modelcontextprotocol/express, and the zod validation library.
  • [COMMAND_EXECUTION]: The skill includes standard development commands for initializing, building, and testing MCP servers.
  • Evidence: Examples using npm init, npm install, and npx @modelcontextprotocol/inspector for local development workflows.
  • [DATA_EXFILTRATION]: The skill provides explicit guidance on the secure handling of sensitive data and credentials.
  • Evidence: Specifically warns against hardcoding secrets in configuration files and demonstrates passing API keys via the env field in Claude Desktop configuration.
  • [PROMPT_INJECTION]: The skill provides design patterns for building tools that process external data while maintaining safety.
  • Evidence: The elicitation.md file defines security rules for collecting user input, including the use of 'URL mode' for sensitive information to prevent it from entering the LLM's context window.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 07:33 PM