mcp-builder

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The evaluation harness (scripts/evaluation.py) is designed to launch and interact with local MCP servers. It executes commands provided via command-line arguments to start the server processes for testing, which is standard functionality for MCP development tools.
  • [EXTERNAL_DOWNLOADS]: The documentation and instructions suggest fetching reference material from official and well-known sources, specifically modelcontextprotocol.io and the modelcontextprotocol GitHub organization. These are official repositories for the protocol being documented.
  • [SAFE]: The skill implements and teaches security best practices, such as using environment variables for API keys and performing strict input validation using Pydantic or Zod. The code in the scripts/ directory is a legitimate implementation of an MCP client and evaluation runner.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 01:36 AM
Security Audit — agent-trust-hub — mcp-builder