Temur Khan

MCP server exposing OpenClaw token-usage and cost telemetry — per-provider/per-agent attribution, cost-spike anomaly detection, model-routing recommendations, monthly forecasts.

MCP server that vets ClawHub skills before installation — detects prompt-injection patterns, exfiltration, suspicious dependencies, manifest/permission mismatches. Outputs risk score + flagged findings.

MCP server for safe OpenClaw upgrades — version-aware regression catalog, pre-upgrade snapshot, post-upgrade verification, rollback guide. Read-only advisor: never executes the upgrade itself.

MCP server that vets LLM-emitted shell commands BEFORE execution. Detects rm -rf in chains, package-glob removal, dd/mkfs/wipefs, chmod 777, curl|bash, chained shutdown, git destructive ops. 24 rules / 8 families. Sub-second, local, no API key. Defensive complement to MCPShell/mcp-shell/mcp-bash.

MCP server exposing OpenClaw deployment health — gateway status, resource pressure, error trends, skill-registry integrity, upgrade history, disk usage.

MCP server for verifying AI agent claims vs reality — inline grounding-check on retrieval context, swallowed-exception scanner on agent-written code, and multi-turn transcript review for unverified completions + cross-turn contradictions. Sub-second, local, free, MCP-native — the lightweight complement to dashboard-based eval frameworks (DeepEval, Phoenix, LangSmith).

MCP server for cron silent-failure detection across crontab, systemd, and OpenClaw schedulers.