The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

Qiita (LLM)Japan

MCPツールの権限設計と危険なツール呼び出しを防ぐ実践ガイド

10.30

MCP（Model Context Protocol）では、LLMが外部のAPI、データベース、ファイルシステムなどを操作できます。便利な一方で、ツールを追加するだけでモデルに強い権限を与えてしまう危険があります。結論から言うと、readOnlyHint などのメタデータ...

MCP, skills & tools

Read at Qiita (LLM) ↗

One letter a week, starting soon.

Latest

MCPツールの権限設計と危険なツール呼び出しを防ぐ実践ガイド

Related

JapanClaude Tool Runnerで「独自ツールを呼ぶAIエージェント」をTypeScriptで実装する Zenn (AI)

JapanAWS Transform、Azure Functions用のコードをAWS Lambda用に変換など、Microsoft AzureからAWSへの移行に対応 Publickey

JapanWith great verification comes great velocity: How agents raised the stakes at Flava API Gateway LINE Engineering

Japan開発途中でAIモデルやエージェントを替えても品質を落とさない：リポジトリに残す3原則 Qiita (LLM)

GitHubArticle: InfoQ AI, ML and Data Engineering Trends Report - 2026 InfoQ AI

GitHubPodcast: AI, ML, and Data Engineering InfoQ Trends Report 2026 InfoQ AI