Tag: security
All the articles with the tag "security".
-
Stop giving AI agents service accounts
Service accounts were built for predictable software. Agents are different: they act for people, cross tools, and change context. Identity needs to follow the agent, the user, and the task.
-
LangChain made MCP boring, which is exactly when architecture matters
LangChain moving MCP into langchain.mcp is useful because it removes adapter plumbing. It is also a reminder that easier tool access does not remove the need for identity, policy, and ownership.
-
MCP needs an enterprise control plane
Model Context Protocol can make agents useful inside large companies, but only if it is wrapped in identity, policy, audit, ownership, and a serious gateway architecture.