mcp-builder

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official SDKs and documentation from the Model Context Protocol organization on GitHub and its official website. These are well-known resources for developers building MCP integrations.\n- [COMMAND_EXECUTION]: The evaluation harness in scripts/evaluation.py executes local commands to launch MCP servers for automated testing purposes, which is a core feature of the development environment.\n- [SAFE]: The implementation guides and scripts follow security best practices, such as recommending environment variables for secret management and utilizing strict schema validation (Zod and Pydantic) for tool inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 03:40 AM