Skip to main content

​
What are Tool Policies?

Tool Policies allow you to monitor actions taken by AI coding tools in your organization. Create policies to track terminal commands executed by AI agents or MCP tool calls made through integrated servers like GitHub, Linear, Sentry, and more. Gateway URL: https://gateway.getunbound.ai/tool-policies/policies

Tool Policies Dashboard

Click here to access the Tool Policies management interface

​
Policy Types

When you click Create Policy, you’ll be asked to choose what you want to monitor: Create Policy Modal Screenshot placeholder: Show the “Create Policy” modal with the question “What do you want to monitor?” and the two options below

​
Terminal Commands

Monitor shell commands executed by AI coding tools like Claude Code, Cursor, Roo Code, and Cline.
  • Select a Command Family (e.g., delete_file, git_action, remote_access)
  • Define a Target Pattern to match specific paths, branches, or operations
  • Supports exact match, glob patterns (/etc/*), and regex (.*\.env$)

​
MCP Actions

Monitor tool calls made through MCP (Model Context Protocol) servers.
  • Select an MCP Server (e.g., GitHub, Linear, Sentry)
  • Select the MCP Tool to monitor (e.g., create_pull_request, create_issue)

​
Quick Example

Let’s create a policy to audit when AI tools delete files in sensitive directories:
  1. Go to Tool Policies and click Create Policy
  2. Select Terminal Commands
  3. Fill in the form:
    • Name: “Audit Sensitive File Deletions”
    • Command Family: delete_file
    • Target Field: path
    • Target Pattern: /etc/* or *.env
  4. Set Action to Audit
  5. Click Preview Impact to see historical matches
  6. Click Create Policy
Create Terminal Policy Example Screenshot placeholder: Show the completed Create Terminal Policy form with the example values filled in

​
Key Features

  • Application Scope: Apply policies to all applications or select specific ones
  • Preview Impact: See how many historical commands match your policy before deploying
Policy matches are logged and can be reviewed in the analytics dashboard to identify unusual activity patterns and users who may need additional guidance.

Introduction

Learn more about Unbound Security AI Gateway

FAQs

Find answers to common questions