6 results found
Where AI Should Run: Chat Apps, Local LLMs, MCP, APIs, CLIs, and AgentOS
A visual guide to understanding where AI should run, including local LLMs, chat apps, coding agents, MCP, APIs, CLIs, AgentOS, and BYO LLM architectures. Learn how context, tools, permissions, and governance shape the right AI workflow.
Responsibilities of Skills, MCP, CLIs, and APIs
Clarifies responsibilities across Skills, MCP servers, CLIs, and APIs for AI dev workflows—keeping auth, permissions, and audit boundaries clean.
AI will not live in one place, but trust has to
This article discusses the tension between rapidly expanding enterprise AI capabilities and the need for strong governance, introducing a two-layer architecture: off-platform AI for experimental reach and on-platform AI for trusted, governed execution. It explains how combining both layers allows organizations to benefit from flexible, distributed AI while maintaining oversight, brand integrity, and risk management.
Agents are users now and this website is ready
AI assistants are now part of every developer's workflow. This post covers why we built developers.contentstack.com to serve both humans and agents, and how to connect any MCP-capable client to start building on top of it in minutes.
Build context-aware MCPs, not API wrappers
Discover why simply wrapping APIs isn't enough for Model Context Protocol (MCP) servers. Learn how adding project and user context can transform MCPs into dynamic, efficient engines that enhance AI reasoning, reduce errors, and scale across complex environments.
How to build your own MCP server with Contentstack's tools API
Learn how to build a custom MCP server using Contentstack Tools API: fetch tool definitions, register MCP tools, proxy calls to REST/GraphQL, and add controls.