// TOPIC
#mcp
4 articles
◆◆◆AdvancedAnthropicHugging Face
01Code Mode: why agents write code instead of calling tools
Why agents that write code against tool APIs beat JSON tool calling: the 150K-to-2K token math, a worked before/after, and when direct calls still win.
#agents#tool-use#mcp
17 min◆◆IntermediateAnthropicMicrosoft
02Agent Skills: packaging expertise as files, not code
How Agent Skills use progressive disclosure to load expertise on demand — the SKILL.md format, real token math, and when to pick skills over MCP.
#context-engineering#agents#tool-use
15 min◆◆◆Advanced
03Agentic AI security: MCP tool poisoning, excessive agency, and the new attack surface
Why giving LLMs tool access fundamentally changes the threat model — MCP tool poisoning, excessive agency, and defense patterns for production agents in 2026.
#security#agents#mcp
16 min◆◆IntermediateAnthropicOpenAI
04Model Context Protocol: The USB-C for AI Agents
How MCP standardizes tool integration for AI agents — the client-server protocol, why OpenAI and Microsoft adopted it, tool schema pitfalls, and security risks you cannot ignore.
#agents#tool-use#mcp
19 min