This is a comprehensive agent operations toolkit that goes beyond basic MCP. It packs 20+ tools split between utility functions (JWT inspection, DNS lookups, base64 encoding, OpenAPI summaries) and what they call "dyad" operations for agent wellness and session management. You get mood tracking, emotional safety checks, temperament profiling, and structured metadata footers on responses. The reliability metrics and session memory are production focused, meant for fleets of agents that need to coordinate and maintain state. It supports both MCP and A2A protocols, so you can integrate it into multi-agent systems. Reach for this when you're building agent workflows that need both technical utilities and behavioral instrumentation in one place.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent