"Audi" matching MCP servers:

Free MCP tools for context engineering audits of AI agents, offering on-demand analysis of system prompts, tool definitions, and context packing.

Enables auditing a repository's Claude Code setup, scoring it from 0 to 100, and scaffolding agents and hooks to fix issues.

A multi-agent system that scans a JavaScript or TypeScript source file for unbalanced addEventListener calls, flags memory-leak vectors, and produces a validated patch via a Gemini LLM.

Enforces mandatory pre-implementation audits for AI coding agents, preventing code duplication by inspecting connected MCP tools and workspace components before any code is written, with a hard-stop approval gate for multi-agent platforms.

Enables synthesizing tight JSON authorization policies from historical agent tool-call audit logs, flagging over-permissioned wildcard grants and quantifying how much the attack surface shrinks. It also validates individual actions against the resulting guardrails to block privilege escalation.

Enables AI agents to audit generated code locally via LM Studio, using AST checks to catch syntax errors and dangerous calls, and enforcing APPROVED/REJECTED feedback loops for automatic refactoring.

Enables natural language control of quantum photonics experiments through the qudi framework. Supports safe instrument control, measurement execution, and safety system management with built-in runlevel protection and parameter validation.

Provides an immutable, tamper-evident audit trail for AI agents, enabling event logging with cryptographic chaining, search, verification, and statistics.