{"id":"vibe-check-mcp-server","name":"Vibe Check MCP Server","homepage":"https://github.com/PV-Bhat/vibe-check-mcp-server","repo_url":"https://github.com/PV-Bhat/vibe-check-mcp-server","category":"ai-agent","subcategories":["agent-oversight","meta-cognition","mcp"],"tags":["mcp","agent-safety","meta-cognition","anti-tunnel-vision","llm","gemini","openai","anthropic","open-source","node"],"what_it_does":"Vibe Check is an MCP server that acts as a meta-mentor for AI agents, using Chain-Pattern Interrupts (CPI) to challenge assumptions, prevent tunnel vision and over-engineering, and enforce session-specific rules — research shows CPI roughly doubles agent task success rates in evaluation runs.","use_cases":["Adding a reflective pause mechanism to AI coding agents that catches runaway complexity and off-track strategies mid-task","Logging agent mistakes and successful patterns per-session to build a learning feedback loop via vibe_learn","Enforcing per-session behavioral rules (e.g., 'always prefer minimal solutions') that the agent must check via update_constitution"],"not_for":["Latency-sensitive pipelines where adding an LLM oversight call at each step is prohibitive","Simple, well-bounded tasks where agent tunnel vision is unlikely","Teams without API keys for at least one supported LLM provider (Gemini, OpenAI, Anthropic, or OpenRouter)"],"best_when":"You have an AI agent working on complex, open-ended coding or research tasks where you've observed it going off-track, over-engineering, or getting stuck in a flawed strategy — and you want a lightweight oversight layer backed by research.","avoid_when":"Your agent tasks are short, well-defined, and deterministic, where the overhead of a meta-mentor LLM call at each step would outweigh the benefit.","alternatives":["custom-reflection-prompts","langchain-evaluators","constitutional-ai"],"af_score":75.7,"security_score":72.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github","github_awesome"],"priority":"low","status":"evaluated","version_evaluated":"latest","last_evaluated":"2026-03-01T09:50:06.362127+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}