mcp-builder

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides guidelines, reference manuals, and utility scripts for developing Model Context Protocol (MCP) servers in Python and TypeScript. The included Python source files (scripts/connections.py and scripts/evaluation.py) implement standard connection management and an automated evaluation test harness using official, verified SDK libraries (mcp and anthropic). No malicious patterns, prompt injections, code obfuscation, or unauthorized data exfiltration behaviors were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:29 AM
Security Audit — agent-trust-hub — mcp-builder