How the shift from MCP tools to agent skills changed the way AI assistants work with Nx monorepos — and why MCP still matters.

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

The burden of reserving context tokens made me turn of nearly all of the mcps, now only keeping very few.

i use only database mcp, although there is inline cli command , but i need multiple environment connection for daily use. beside those database mcp, i remove it .

As for context management, simpler might be the best way, also in terms of performance:
<a href="https://vercel.com/blog/agents-md-outperforms-skills-in-our-agent-evals" target="_blank" rel="noopener nofollow">https://vercel.com/blog/agents-md-outperforms-skills-in-our-agent-evals</a>