Mcp Audit

Connects to Anthropic's API using your own key to run context engineering audits on AI agent configurations. Exposes three tools: audit_system_prompt for finding instruction conflicts and role clarity issues, audit_tool_definition for checking function call reliability problems, and audit_context_packing for spotting redundancy and truncation risks. Returns top three findings per scan with severity rankings and specific recommendations. Useful when you're debugging why an agent isn't following instructions or when tools aren't getting called reliably. The audit engine applies Archonics' methodology but runs client side, so your prompts never hit their servers. Free tier gives you quick feedback; paid tiers available if you need full reports.