Skip to content

SCC vs Local Claude Code

This guide compares running Claude Code through SCC’s Docker sandbox versus running it directly on your local machine.

AspectSCC CLILocal Claude Code
Execution environmentDocker containerYour host machine
File accessOnly mounted pathsFull filesystem
Git protectionSafety Net blocks destructive commandsRelies on Claude’s built-in behavior
ConfigurationCentralized org/team profilesPer-user ~/.claude/ settings
Plugin controlOrg-approved plugins onlyAny plugin
Setupscc setup + scc startclaude directly

With SCC, Claude Code runs inside a Docker container. The AI can only access files in paths you explicitly mount—typically your project directory.

Terminal window
# SCC mounts only the workspace
scc start ~/my-project
# Claude Code sees /home/user/my-project inside container
# Cannot access ~/.ssh, ~/.aws, or other host paths

Running Claude Code locally gives it access to your full filesystem (within the permissions of your user account).

SCC’s Safety Net plugin blocks commands that can cause data loss:

Blocked CommandRisk
git push --forceOverwrites remote history
git reset --hardDiscards uncommitted changes
git branch -DForce-deletes branches
git clean -fdDeletes untracked files

Local Claude Code relies on its own judgment and your confirmation prompts.

SCC lets organizations define:

  • Approved plugins: Only whitelisted plugins can run
  • MCP servers: Control which external services Claude can access
  • Security policies: Network posture, blocked patterns
  • Team profiles: Consistent defaults across developers

Developers run scc setup once to inherit all team settings.

With local Claude Code, each developer manages their own ~/.claude/ configuration independently.

SCC provides built-in worktree management for parallel AI tasks:

Terminal window
scc worktree create ~/project feature-auth
# Creates isolated branch scc/feature-auth
# Claude experiments don't touch main branch

This keeps AI work isolated from your main development branch.

  • Your team needs consistent Claude Code configurations
  • You want Docker isolation between AI and host system
  • You need to prevent destructive git operations
  • Org admins must control which plugins are allowed
  • Multiple developers need standardized setups
  • You’re a solo developer with simple needs
  • You need maximum speed (no container startup)
  • You trust Claude Code’s built-in safety measures
  • You don’t need team-wide governance

Some teams use both:

  • Local Claude Code for quick, trusted tasks
  • SCC for experimental work or when working with sensitive code