mcp-builder
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Retrieves protocol specifications and SDK documentation from official project sources, including modelcontextprotocol.io and the official GitHub repositories for the MCP project. This is used to provide the agent with current technical documentation.
- [COMMAND_EXECUTION]: The evaluation framework (scripts/evaluation.py) supports the execution of local MCP servers through the stdio transport. This functionality allows developers to launch and test their own server implementations in a local environment, which is the primary purpose of the skill.
- [CREDENTIALS_UNSAFE]: The documentation and guides within the skill explicitly recommend using environment variables for managing sensitive API keys and tokens, adhering to secure development standards.
Audit Metadata