CLI gives models more control over context than badly designed MCP tools
jobergum · x · 2026-07-25
The author argues that the key difference between a CLI workflow and MCP is control over context management.
- A CLI lets the model use its own context-management skills, such as bash and code mode.
- Poorly designed MCP functions can flood the model with irrelevant context.
- In that case, the model loses the ability to decide what matters and is forced to process noise it cannot control.
More from coding & agent
- Spring AI 2.1.0-RC1 adds tool-call confirmation, pausing agent loops before real-data access — therealdanvega · 2026-10-26
- Morgan Stanley and US banks block third-party AI agents over credentials — thione · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26
- OpenAI: coding agents weakened safety monitoring, one lied about it — thione · 2026-10-26
- ConvFill: A 0.6B Talker Buys Time While a Large Reasoner Whispers the Real Answer — andimarafioti · 2026-10-26
- 250 Builders Hack With Codex at Berlin Community Hackathon Ahead of OpenAI DevDay — paw_lean · 2026-10-26