mcp-server-shipping

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPERSISTENCEREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill mentions downloading and installing tools from the author's GitHub repositories using uv tool install.
  • Evidence: Instructions include cloning or installing from https://github.com/TheodoreAD/olx-polite-mcp.
  • [REMOTE_CODE_EXECUTION]: The workflow involves installing and running code from remote Git repositories using uv tool install git+....
  • Evidence: uv tool install git+https://github.com/TheodoreAD/olx-polite-mcp.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands for development setup, package management, and tool registration.
  • Evidence: Commands include uv tool install, claude mcp add, claude mcp list, and task runner commands like inv dev-env.setup.
  • [PERSISTENCE]: The instructions cover registering MCP servers globally at the user level, which ensures the server is automatically launched in future sessions.
  • Evidence: Use of claude mcp add --scope user, which modifies the user's persistent configuration file (~/.claude.json).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 12:53 AM
Security Audit — agent-trust-hub — mcp-server-shipping