What interactions with internal tools? If you can answer that question then the clankers can help you write a deterministic program for that same interaction and you only spend the tokens once.
Sharing Slack with Claude:
- Using the "normal" way, it shares too much, including privates messages.
- Using your own token, it doesn't work with Claude.AI or Cowork and requires you to go to slack.com to generate an application, tokens and more.
- Using a shared token, now you need context to tell Claude to retrieve it. It still doesn't work for non-Claude Code workflows. Rotation may break currently running workflows.
Less token spend, lower latency, more predictable results compared to having the LLM perform the task directly every time.
The MCP is the deterministic program.
You need to take a step back and look at the problem you're discussing. What's exactly this MCP thing? It's a protocol to allow agents and coding assistants to access tools, services, and data sources, through a standardized interface.
It's the interface for your deterministic program. That's it.
That only applies if you are talking about a well established recurrent workflow. That's not how MCPs are used to begin with.
Best of both worlds in my view.