mcp-server-deployment

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the mcp-publisher CLI tool via Homebrew and the @anthropic-ai/mcpb package from npm. These tools are part of the trusted ecosystem for the Model Context Protocol and are used for their intended distribution purposes.
  • [COMMAND_EXECUTION]: The skill uses a local Python script check_server_json.py to validate the server.json manifest. This script is limited to performing structure and regex validation on local JSON files and does not perform network operations or access sensitive system paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 10:44 AM
Security Audit — agent-trust-hub — mcp-server-deployment