Your LLM Does Not Care About MCP(hackteam.io)
hackteam.io
Your LLM Does Not Care About MCP
https://hackteam.io/blog/your-llm-does-not-care-about-mcp/
2 comments
>But to your LLM, there’s no difference between “regular” tool calling and using a standard like MCP.
The difference is that it's trained and benchmarked on the MCP-standard. Which makes it much more reliable than if you create your own interface.
The difference is that it's trained and benchmarked on the MCP-standard. Which makes it much more reliable than if you create your own interface.
Also, what are the best strategies to rigorously validate inputs while minimizing latency?
Is this the best for Rust: https://github.com/modelcontextprotocol/rust-sdk