Question 278
Scenario: Code Generation with Claude Code
A team uses Claude Code daily for generating, refactoring, debugging and documenting code — with custom slash commands, CLAUDE.md configuration, hooks, and judgment about when plan mode beats direct execution.
Read the full scenario lessonA team is evaluating their Claude Code setup and wants to understand the permission model. They add a new tool via MCP that can execute shell commands. When an agent tries to use this tool, it gets a permission error. Where are MCP tool permissions managed?