Skip to main content
Augment Code is an AI coding assistant built for large, complex codebases. Its context engine indexes your entire repository — architecture, dependencies, internal APIs, and naming conventions — to power chat, completions, and an agent that edits files, runs commands, and calls MCP tools. It works in the VS Code extension and the Auggie CLI.

​
Prerequisites

Before setting up the integration, ensure you have:

​
Setup with Unbound CLI

This installs the Unbound hooks for Augment Code. Both the VS Code extension and the Auggie CLI pick up the same hooks. Reload the VS Code window (and restart your terminal) after setup. To remove the Unbound configuration:

​
Usage

​
Basic Usage

After configuration, every tool call Augment makes — shell commands, file reads, file writes, edits, and MCP actions — is checked against your policies before the tool runs. A matching Block policy stops the call and tells the agent why. Audit records it. Setup also writes Augment’s own ask-user rules into ~/.augment/settings.json — open that file after setup to see them. They cover the highest-risk shell commands: rm -rf, piping a download into a shell, sudo, chmod 777, a force push, and reads of /etc/shadow, .aws/credentials, ~/.ssh keys, .netrc and .env. A second rule targets MCP tool calls, but don’t count on a prompt there. Rules you added yourself are kept, and re-running setup doesn’t duplicate ours.
Block and Audit are the actions that land on Augment today. A Warn policy allows the command and records it — the same outcome as Audit — with the shell rules above as the developer-facing stop. Require Slack Approval is not ready here: the first attempt is denied with a message telling the agent to retry, and the retry times out before an approver can answer. Use Block where the command must not run.

​
Security Benefits

Using Augment Code with Unbound Security AI Gateway provides:
  • Request Monitoring: All Augment tool calls are logged and monitored
  • Analytics: See which files and commands Augment touches across your org
  • Compliance: Ensure AI interactions meet your organization’s standards
  • Audit Trail: Complete visibility into AI usage patterns

Unbound CLI

Install the CLI to set up and manage tools

Tool Policies

Configure security guardrails for AI tools