mitsuhiko: unstable tool outputs explain codemode failures; OpenAPI + embeddings work great
mitsuhiko · x · 2026-09-16
In the MCP vs CLI/codemode debate, mitsuhiko diagnoses the problem: existing servers rarely return stable, structured outputs from tools. He found OpenAPI-style APIs work excellently with codemode, especially paired with a basic embedding model to surface API specs to the agent.
Related event: Developers Converge: MCP Now Beats CLI for Most Agent Integrations(9 posts)→
More from coding & agent
- 10 must-know topics for RAG engineer interviews: chunking, retrieval metrics, hallucination debugging — ashishllm · 2026-09-16
- Third-party Grok Bot turns YouTube lectures into exam-ready cheat sheet PDFs — tetsuoai · 2026-09-16
- Jev programming likened to MapReduce for decisions: parallel, mutually unaware queries — cocktailpeanut · 2026-09-16
- 53 MCP servers scanned: 36% graded D/F, mostly for over-permissioned scope — BrilliantSecret143 · 2026-09-16
- Claude Code's auto mode quietly uses a second safety classifier model, sparking Max-tier transparency complaints — tomekkorbak · 2026-09-16
- When an LLM plans an executable agent DAG, where do you draw the trust boundary? — Repulsive_Sugar_5252 · 2026-09-16