Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop.
Score your agent's governance (0-100), lint MCP tool definitions, and estimate costs across all major models. Free diagnostic tools with no API key needed. Expert skill files on governance, economics, and system architecture available with free tier.
A read-only MCP server that exposes local coding-agent session logs as three tools for introspection of recent work, debugging tool failures, and tracking token usage and estimated cost without parsing log files.
Token-cost telemetry for OpenClaw, queryable from Claude or any MCP-aware agent. Provides per-agent and per-provider cost attribution, anomaly detection, model-routing recommendations, and 30-day forecasts.
Enumerates everything in a code checkout addressed to an AI agent, including instruction files, hook commands, declared MCP servers, and skills/subagents, so you can review what your agent will actually follow.
Audits AI agent skills for safety using static, semantic, adversarial, and supply-chain analysis, providing scores and risk flags. Can be run via CLI, CI, or as an MCP tool from Claude Code, Cursor, and Codex.