mcp-server-design
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides comprehensive guidelines for designing MCP server surfaces, focusing on improving agent tool-selection accuracy and context management.
- [SAFE]: The included script
scripts/lint_tool_surface.pyperforms static analysis on local JSON files. It uses only Python standard libraries (json,re,sys) and does not execute network requests, access sensitive files, or perform dynamic code execution. - [SAFE]: All external references, including those to
github.com/modelcontextprotocol/servers,modelcontextprotocol.io, andgithub.com/anthropics/skills, point to official project documentation or trusted organization repositories. - [SAFE]: The skill does not contain any prompt injection patterns, obfuscation, or attempts at persistence or privilege escalation.
Audit Metadata