mcp-builder

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and README files from external sources to guide development.
  • Fetches protocol specifications from modelcontextprotocol.io.
  • Fetches SDK documentation from the modelcontextprotocol organization on GitHub (e.g., https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md).
  • [COMMAND_EXECUTION]: The documentation includes various command-line instructions for building, testing, and evaluating MCP servers.
  • Node.js/TypeScript commands: npm run build, npx @modelcontextprotocol/inspector.
  • Python commands: python -m py_compile, python scripts/evaluation.py.
  • [REMOTE_CODE_EXECUTION]: The evaluation guide provides a template command to execute a local Python script (scripts/evaluation.py). While the script itself is not included in the skill files, the command is presented as an instructional example for developers to test their own implementations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 08:12 AM