Mcp on Aleph Beth https://www.alephbeth.ai/tags/mcp/ Recent content in Mcp on Aleph Beth Aleph Beth https://www.alephbeth.ai/og-image.jpg https://www.alephbeth.ai/og-image.jpg Hugo en-US Mon, 29 Jun 2026 00:00:00 +0000 When AI Takes Action: Understanding Attacks on Autonomous Agents, and How to Defend Against Them https://www.alephbeth.ai/posts/2026-06-29-ai-agent-security-jailbreak-countermeasures/ Mon, 29 Jun 2026 00:00:00 +0000 https://www.alephbeth.ai/posts/2026-06-29-ai-agent-security-jailbreak-countermeasures/ A chatbot writes sentences; an AI agent acts — it reads your email, runs code, calls APIs, spends money. That shift moves the risk: it is no longer about making the AI say something forbidden, but about making it do something dangerous. This article explains, with detailed and accessible examples, how these attacks actually work, why naive guardrails fail, and what a decision-maker must demand before putting an agent into production. Claude Desktop — Simple Hardening: What Claude Should NOT Have Access To https://www.alephbeth.ai/posts/2026-04-27-claude-desktop-simple-hardening/ Mon, 27 Apr 2026 00:00:00 +0000 https://www.alephbeth.ai/posts/2026-04-27-claude-desktop-simple-hardening/ Targeted attack-surface reduction for Claude Desktop. Simple principle: it’s a chat assistant, not a system agent. The list of NOs, the list of OKs, and a 30-minute checklist.