Introduction

​

What is Unbound Security?

Unbound Security is an Agent Access Security Broker (AASB) that helps organizations discover, assess, and enforce policy for AI coding agents. Unbound gives security teams full visibility and control over every agent, tool, and action — covering terminal commands, file access, MCP connections, and IDE plugins across tools like Claude Code, Cursor, Cline, GitHub Copilot, and Devin Desktop.

​

Key Capabilities

​

Agent Discovery

• Inventory AI coding agents in use: Detect Claude Code, Cursor, Devin Desktop, GitHub Copilot, Cline, and more across your engineering org
• Enumerate MCP servers: Surface every MCP server a developer has connected — and the tools each one exposes — so you can see an agent’s real reach, including into risky or unknown servers
• Map IDE plugins: See which AI-powered IDE extensions are installed and how they are configured

​

Risk Assessment

• Per-developer posture scores: A live security signal for each engineer based on the agents, plugins, and MCP servers they have enabled
• Risky MCP connection alerts: Flag MCP servers with excessive permissions or untrusted sources
• Autonomy analysis: Understand how much runway each agent has inside each developer’s environment

​

Policy Enforcement

• Terminal command control: Allow or deny commands by the action they perform, so one rule covers many spellings of the same action — with Custom rules for matching a command line exactly
• MCP policies: Govern which MCP servers and tools each agent can reach
• Approval workflows: Require human approval for sensitive agent actions
• Audit logging: A complete record of what every agent did, for compliance and incident review

​

Data Protection

• Automatic secret detection: Catch API keys, tokens, connection strings and private keys before they leak to an LLM provider, and block or record the attempt
• Personal data detection: Catch PII in prompts, with the identifier types you choose
• Your data stays private: While keeping your teams productive

​

How It Works

Unbound operates as an endpoint-level control plane for AI coding agents.

​

1. Discover

Unbound inventories the AI coding agents, MCP servers, and IDE plugins in use across your engineering org — no agent-by-agent configuration required.

​

2. Assess

Every agent, tool, and action is scored for risk. Security teams get a live posture view: who is running what, which MCP servers are risky, and where policies are missing.

​

3. Enforce

Policies stop an action before it runs — terminal command allow/deny, file access, MCP scope controls and approval workflows.

​

Supported Integrations

• AI Coding Agents: Claude Code, Cursor, Cline, GitHub Copilot, Augment Code, Roo Code, Kilo Code, Codex
• Discovered: Devin Desktop, Google Antigravity, OpenCode, Replit, JetBrains IDEs, Junie, Cursor CLI, Claude Cowork, Claude Desktop, Visual Studio, Xcode Coding Intelligence, OpenClaw and others are inventoried by Discovery — 24 tool families across macOS, Windows and Linux — so you can see where they’re in use across your fleet
• MCP Servers: Policy enforcement across any MCP server a developer connects
• Identity: single sign-on through your organization’s identity provider, plus an Okta directory sync that brings managers, departments and titles onto your Unbound users
• MDM: Auto-configure and deploy agent settings through your device management platform

​

Enterprise Features

​

Security Controls

• Terminal command, MCP, and file access policy enforcement
• Secret and personal-data detection in agent traffic
• Compliance-grade audit logging

​

Management & Visibility

• Per-developer, team, and department posture
• Agent, plugin, and MCP inventory
• Usage insights and recommendations
• Centralized AI coding tool management

​

Getting Started

​

Prerequisites

• Node.js 18+ — required for the CLI. Check with node --version.
• Supported operating systems for the full Quick Start: macOS, Windows, and Linux. The CLI and the device-discovery step (the onboarding wizard’s device scan and unbound discover) run on all three.
• On Linux installs where Node lives in a system path (e.g. the NodeSource apt package), npm install -g writes to a root-owned directory and needs sudo. With a user-scoped Node manager (nvm, fnm, volta) or a custom npm prefix, no sudo is required.

1. Install the CLI: npm install -g unbound-cli (prefix with sudo if npm requires root on your system)
2. Login: unbound login
3. Set up your AI tool — run the command for your tool (pick one). Pass the mode flag so the command stays one-shot in any shell:
   # Pick the one that matches the AI tool you use
   unbound setup cursor
   unbound setup claude-code --subscription
   unbound setup codex --subscription
   unbound setup copilot
   unbound setup augment
   
   Running unbound setup claude-code or unbound setup codex with no flag opens an interactive mode picker, so pass the mode explicitly when you are scripting. See Tool Setup for the full list.
4. Monitor and govern: Track agent activity and enforce policy from the dashboard. New workspaces are routed through a short onboarding wizard at gateway.getunbound.ai/onboarding on first visit — complete the wizard and /dashboard will be available.