vibe-check-mcp-server and interactive-mcp
About vibe-check-mcp-server
PV-Bhat/vibe-check-mcp-server
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks
Implements the Model Context Protocol (MCP) as a meta-mentor layer that invokes a secondary LLM to provide metacognitive feedback and Chain-Pattern Interrupt (CPI) signals, detecting reasoning lock-in through trait analysis and uncertainty scoring before agents commit to irreversible actions. Operates via STDIO and HTTP transports with research-backed efficacy (27% success improvement, 41% reduction in harmful actions), integrating seamlessly with MCP-aware clients like Claude Desktop, Cursor, and Windsurf for real-time agent oversight.
About interactive-mcp
ttommyth/interactive-mcp
Vibe coding should have human in the loop! interactive-mcp: Local, cross-platform MCP server for interact with your AI Agent
Implements five MCP tools that enable bidirectional communication: `request_user_input` with optional predefined choices, OS notifications, and persistent command-line chat sessions for multi-turn interactions. Runs as a local Node.js/TypeScript server communicating via stdio with MCP clients (Claude Desktop, Cursor, VS Code), requiring direct OS access for displaying prompts and notifications. Supports configurable timeouts and granular tool disabling through command-line flags.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work