Smiley Face

Nx shifted from MCP tools to agent skills for AI assistants after recognizing that modern agentic workflows made many MCP tools redundant. Agents can now execute CLI commands directly and process outputs themselves, making context-dumping MCP tools token-inefficient. Skills provide domain-specific knowledge about when and how to use Nx features, while MCP remains valuable for authenticated APIs and process communication. Benchmarks show skills outperform MCP-only approaches, especially for smaller models, with agents using generators more consistently and validating their work more often.

Why we deleted (most of) our MCP tools

Everything about vibe coding 🤖
Tools, tips, tricks, workflows, best practices, you name it.
Let the vibes guide you

Vibe Coding

Trend is to move over to skills over MCPs. But still for authenticated endpoints, MCP is king

Trend is to move over to skills over MCPs. But still for authenticated endpoints, MCP is king

Probably you can just create a cli wrapper for authenticated endpoints too?

Sometimes when using mcps its best to combine them in skills cuz I seen situations specifically with Github mcp for enterprise where agent fails to fetch data due to some constraints which need to be explained.
And for this mcp becoming obsolete thing: I too noticed skills are kind of more powerful. The most annoying disadvantage is that you need to rewrite API calls for different terminals (windows, linux etc).
However I did not get why mcp is inferior when calling auth endpoints (or other processes noted in second point). There are no provided examples how this would be done in skill and how it would suck.
Cuz from my POV either you use mcp or skill you still need keys and you would still need to setup them for both. Will skill thr AI user could guide user, tell them what is missing to successfully call the API.