If you're using an Agent that you built, a pre-built Agent (Claude Code, Ollama locally, etc.), or a provider-based Agentic UI (Gemini, ChatGPT, etc.), the question is - how do you
The running joke is "The S in MCP stands for security", and for good question. Out of the box, there's realistically no way to secure traffic from a user
As teams and the enterprise are figuring out various ways to secure traffic from Agents to LLMs, other Agents, or MCP Servers, what about the lowest barrier to entry? Someone's local
Ensuring that Agents have the proper tools and information they need to perform a specialized action on behalf of a user or a system will be necessary for AI to meet the needs
Although the idea around Agents, MCP Servers, and Agentic workflows is just about all everyone is talking about, it's important to remember that this cohort of work has only been around