I recently added a Model Context Protocol server to Co-op Translator.
Co-op Translator started as a CLI-first tool for translating Markdown files, Jupyter notebooks, and text inside images. The CLI is still the most natural interface when a person wants to translate a repository from a terminal.
But agents see tools differently.
When an agent such as Codex or Claude Code works with a project, it does not only run one big command and walk away. It reads context, chooses a smaller action, checks the result, and then decides the next step. That pushed me to rethink the shape of the Co-op Translator APIs before exposing them through MCP.
This article is about that shift in interface design.
First, a CLI can hide complexity because a human asks it to complete a whole job.
Second, MCP tools need safer defaults because an agent may be operating inside a real workspace.
Third, agent-assisted translation works best when Co-op Translator owns the document workflow and the host agent owns the language…