𝗧𝗵𝗲 𝗗𝗮𝘆 𝗔𝗜 𝗔𝗿𝗴𝘂𝗲𝗱 𝗪𝗶𝘁𝗵 𝗠𝗗𝗡 𝗔𝗻𝗱 𝗟𝗼𝘀𝘁

AI coding assistants change how you write software. They write tests. They explain APIs. They review code.

But they fail at one specific task: knowing what browsers support today.

Mozilla tested this recently. They used Claude Code to ask about new Firefox features. The AI claimed Firefox did not support the Web Serial API. It even said Mozilla had no plans to support it.

The AI was wrong. Firefox had already shipped that feature.

This happens because the web moves faster than AI training data. Browsers ship new APIs and CSS features every few weeks. An AI model trained months ago simply does not know these changes exist. It fills the gaps with old data.

Mozilla built a solution: the MDN MCP Server.

MCP stands for Model Context Protocol. It lets AI models connect to external data. Instead of relying on memory, the AI checks the source.

Old way: Developer -> AI Memory -> Answer

New way: Developer -> AI -> MDN -> Answer

The MDN MCP Server gives the AI access to documentation and browser compatibility data. When Mozilla tested this, the results changed.

Surprisingly, the AI became twice as fast. It no longer spends time searching the web or parsing HTML. It gets structured data directly.

You can use this with many tools, including:

To add it to Claude Code, run this command: claude mcp add --transport http mdn https://mcp.mdn.mozilla.net/

The lesson is simple. AI does not need a bigger brain. It needs better access to facts. The future of coding is not AI replacing documentation. It is AI reading the documentation with you.

Source: https://dev.to/josephciullo/the-day-ai-argued-with-mdn-and-lost-mm7