Tag: mcp
All the articles with the tag "mcp".
-
Better Context Beats a Stronger Model — repowise's Five-Layer Architecture
I came across repowise, a tool that inserts a layer of context between your codebase and the model. It is a good excuse to talk about a bigger idea: when a model breaks things, the first instinct is to reach for a stronger model, but the real cause is usually too little context.
-
給 LLM 更好的 context，勝過換更強的模型——repowise 的五層架構
看到 repowise 這個在 codebase 與模型之間插一層 context 的工具，想聊一個更大的觀念：模型改壞東西時，第一反應常常是換更強的模型，但真正的根因往往是 context 不夠。
-
Have Claude scan an MCP before you install it—it found 7 vulnerabilities and still said it's safe to install
This week AgentCrew Academy shipped a video about why you should run /security-scan before installing any MCP / npm / pip package. Tested a third-party MCP, Claude flagged 7 findings, then said "install is fine." This is the written companion to the video.
-
裝 MCP 之前先讓 Claude 幫你掃——找到 7 個漏洞，但說這個可以裝
講座當週我拍了一支影片，講「裝任何 MCP / npm / pip / clone 之前先跑 /security-scan」這件事。實測了一個三方 MCP，Claude 掃出 7 個漏洞，但綜合評估後說「可以裝」。這篇是影片的補充文字版。
-
Two MCP servers for Taiwan public data—what mcp-taiwan-legal-db and Twinkle Hub are each good for
Two MCP servers wrapping Taiwan's public data sources—one focused on court judgments and statutes, the other aggregating 52,960 government open datasets plus 37 local utility tools. They turn out to be complementary; I now run both.
-
台灣公開資料兩個 MCP 評測——mcp-taiwan-legal-db 跟 Twinkle Hub 各適合什麼場景
兩個串接台灣公開資料的 MCP server——一個專精法律判決跟法規查詢、一個聚合 5.3 萬筆政府開放資料 + 37 個在地工具。實測下來各有強項，課程跟顧問場景的搭配方式不一樣。