building-mcp-servers

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a development framework and documentation library for building MCP servers. All provided scripts and instructions align with this stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation and SDKs from 'modelcontextprotocol.io' and 'github.com/modelcontextprotocol'. These are well-known, authoritative sources for the protocol and are used to fetch reference materials neutrally.
  • [COMMAND_EXECUTION]: The evaluation script ('scripts/evaluation.py') allows developers to run their MCP servers locally for testing. This command execution is initiated by the user via the command-line interface and is confined to the intended development and testing context.
  • [DATA_EXFILTRATION]: No suspicious data handling or exfiltration patterns were identified. The use of API clients (Anthropic) and transport protocols (SSE, HTTP, stdio) is standard for MCP integrations and server-to-client communication.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:24 AM
Security Audit — agent-trust-hub — building-mcp-servers