Making Langgraph agent states and memories inspecatble

Often, during development and production of agentic, montoring traces themselves is not enough, especially when issues might lie in the state checkpointers or in the memory stores. I built an mcp called LangMCP that helps connect with your checkpointers and memory stores to debug and retrieve information for analysis

https://medium.com/towards-artificial-intelligence/ai-agents-need-inspectable-state-thats-why-i-built-langmcp-6038cca8a1d9