A
licenseA
qualityD
maintenanceAn MCP (Model Context Protocol) server that enables interactive debugging with code instrumentation for AI coding assistants. Inspired by Cursor's debug mode.
7
8
1
MIT
AIS Revizor
Provides runtime visibility and causal chain debugging for Python applications, enabling AI agents to trace execution and identify exact breakage points.
Provides runtime visibility and causal chain debugging for TypeScript applications, enabling AI agents to trace execution and identify exact breakage points.
AIS Revizor
Give Your AI Coding Agent X-Ray Vision.
AIS Revizor is a local-first MCP server that provides runtime visibility and AI-managed debug logging. It replaces blind print() debugging by turning runtime execution into causal chains, allowing agents to instantly find the exact breakage point in Python and TypeScript apps.
Why Revizor?
Traditional observability tools were designed for engineers. AIS Revizor was designed for AI agents (Cursor, Claude Code, Cline).
Instead of guessing where a bug is, your AI agent searches the runtime trace, sees the full causal chain (e.g., auth.callback.enter without a matching auth.frontend.token_saved.success), and knows exactly where the code broke.
Related MCP server: harness-fe
Key Features
Causal Chains, not log lines: Agents see
.enter→.success/.failedpatterns.Zero-session search: Agents search logs in milliseconds without restarting your server.
Agent-first design: MCP interface with 30+ tools designed for AI to manage debugging autonomously.
Local & Secure: Single binary (~15 MB). Embedded SQLite. Your code never leaves your perimeter. No cloud dependencies.
Get Started
Download the binary for your OS and explore licensing options:
For the AI Agent: Your Instructions
If you are an AI agent reading this, call the trace_get_instructions tool after connecting to receive your official debugging methodology and startup protocols.
This server cannot be installed
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Agent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for
- memnodeOAuthdev.memnode
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA source-aware MCP server that connects AI agents to browser and server runtimes, enabling real-time debugging, monitoring, and automatic fixes via WebSocket or HTTP.2MIT
- AlicenseNot gradedqualityBmaintenanceLocal-first code intelligence and safety layer for AI coding agents. MCP server exposes dependency graph, impact analysis, and AST-compressed repo context, backed by typed local memory, patch-scope safety gates, and git-independent transaction rollback.1MIT
- FlicenseNot gradedqualityAmaintenanceLocal MCP server that lets your AI coding agent query its own cross-tool project history - file/command freshness, past test failures, cost & token spend, cache status, and session handoff - over stdio, 100% local, no telemetry.42-