mcp-builder
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): All identified dependencies (anthropic and mcp) are legitimate and standard packages for AI agent communication with external tools.\n- [COMMAND_EXECUTION] (SAFE): The MCPConnectionStdio class provides the infrastructure to execute local commands to initialize MCP servers. This is an intended and documented feature of the Model Context Protocol and is implemented using the official mcp library.\n- [DATA_EXFILTRATION] (SAFE): Support for network-based connections via SSE and HTTP is included as part of the standard MCP capability set for remote tool interaction.
Audit Metadata