mcp-builder

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Command and Process Execution: The skill includes scripts designed to interact with MCP servers by launching local processes (using the stdio transport) or connecting to remote endpoints (via HTTP/SSE). This capability is central to the skill's purpose of testing and evaluating server implementations.
  • External Documentation Retrieval: The instructions utilize web-fetching capabilities to retrieve protocol specifications and SDK documentation from official sources, including modelcontextprotocol.io and GitHub. These references target well-known repositories associated with the technology being implemented.
  • Data Processing and Tool Interaction: The evaluation script (scripts/evaluation.py) processes external data from XML files to prompt an AI model and interact with server tools. This architecture is standard for an automated testing harness, using structured tags (like <summary> and <response>) to maintain clear boundaries between instructions and data.
  • Environment and Secret Management: The skill follows industry standards for credential handling, instructing users to manage API keys through environment variables rather than hardcoding them in scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 10:35 PM
Security Audit — agent-trust-hub — mcp-builder