openclaw-output-vetter-mcp
MCP server for verifying AI agent claims vs reality — inline grounding-check, swallowed-exception detection, multi-turn contradiction detection. Catches the agent says 'done' but nothing changed pattern.
Install
Install and configure the MCP from https://github.com/temurkhan13/openclaw-output-vetter-mcp now. Follow the repository's installation instructions, ask me for anything you can't complete yourself, and verify its tools load.Related servers
bash-vet-mcptemurkhan13MCP server that vets LLM-emitted shell commands BEFORE execution. 30 detection rules across destructive file ops, package managers, system, database, git, network, exfiltration, privilege escalation. Sub-second, local, free.openclaw-cost-tracker-mcptemurkhan13MCP server for AI agent token-cost telemetry + quota-window awareness across Anthropic, OpenAI, Gemini, Ollama, AWS Bedrock. Per-agent attribution, spend-spike detection, 429-prediction tools.openclaw-health-mcptemurkhan13MCP server for AI agent deployment health — gateway status, CPU/memory/swap, recent errors, skill registry integrity, upgrade outcomes, cron + disk usage. HEALTHY/DEGRADED/CRITICAL classification per component.openclaw-skill-vetter-mcptemurkhan13MCP server for security-vetting third-party AI agent extensions before installation — Claude skills, ClawHub plugins, agent tool packs. 41 detection rules; outputs 0-100 risk score + BLOCK/REVIEW/CAUTION/CLEAN.