Reality-check layer for AI agents. Detect hidden risks, missing context & real-world consequences before your LLM answers or acts. MCP tool for Claude Code & Cursor.
python mcp openai ai-safety ai-agents reality-check guardrails tool-use responsible-ai anthropic risk-detection llm-safety llm-guardrails mcp-server claude-code agent-safety mcp-tool action-gating common-sense-ai consequence-simulation
-
Updated
May 24, 2026 - Python