
MCP-101
A series dedicated to MCP : from basics to development of MCP servers
5 of 12 articles published
Articles on the MCP protocol, AI agent security, and AI press review.

A series dedicated to MCP : from basics to development of MCP servers
5 of 12 articles published

Mini-course
Build mcp-travel, your first Python MCP STDIO server with FastMCP: two mock tools testable in Claude Desktop, Claude Code CLI and OpenCode.
Read more

Press Review
Fable 5 returns after U.S. export controls, Grok 4.5 cuts coding costs, prompt injection hits GitHub Actions: 11 tech and AI articles, July 9, 2026.
Read more

Mini-course
5 MCP attack vectors documented by Invariant Labs and Trail of Bits, with 3 isolation levels: source audit, rootless Docker, and lightweight VM.
Read more

Article
Move beyond iterative prompting: /goal keeps Claude working until a verifiable condition is met; Dynamic Workflows orchestrate up to 1,000 agents via a
Read more

Press Review
Claude Sonnet 5 launches alongside Microsoft Memora; AI agent memory, isolation, infrastructure governance, and LLM cost management in focus.
Read more

News
Anthropic launches Claude Sonnet 5 on June 30, 2026: near Opus 4.8 performance at $2/MTok until Aug 31. Analysis of improvements and agentic use cases.
Read more

Analysis
How to secure AI agents: 7 attack vectors, runtime sandboxing (Docker, Podman, gVisor), layered architecture, and autonomy levels.
Read more

Press Review
VS Code offline mode, open source vs AI agents, OpenAI/Broadcom's Jalapeño chip, Lambda microVMs, agentic AI governance, and data center carbon footprint.
Read more

Analysis
Anthropic now requires passport and biometric data from Claude Free/Pro/Max users starting July 8. Why now? The Fable 5 shutdown timeline and European
Read more