# Unbound Security

## Docs

- [Introduction](https://docs.getunbound.ai/introduction.md): Learn about Unbound Security, the Agent Access Security Broker for AI coding agents
- [Frequently Asked Questions](https://docs.getunbound.ai/faqs.md): Common questions about Unbound Security
- [Unbound CLI](https://docs.getunbound.ai/cli/overview.md): Install and manage the Unbound AI Gateway from your terminal
- [Authentication](https://docs.getunbound.ai/cli/authentication.md): Login, logout, and configure tenant URLs for the Unbound CLI
- [Doctor](https://docs.getunbound.ai/cli/doctor.md): Deep local health check for your Unbound install and connected AI tools
- [Tool Setup](https://docs.getunbound.ai/cli/tool-setup.md): Configure AI coding tools to route through Unbound using the CLI
- [Policy Management](https://docs.getunbound.ai/cli/policies.md): Create, list, and manage all four Unbound policy types from the CLI
- [Users & Groups](https://docs.getunbound.ai/cli/user-management.md): Manage organization members, user groups, and tool connections from the CLI
- [Discovery](https://docs.getunbound.ai/cli/discovery.md): Scan devices for installed AI tools and schedule recurring scans
- [Chat](https://docs.getunbound.ai/cli/chat.md): Query your Unbound usage data with natural language from the terminal
- [Analytics](https://docs.getunbound.ai/cli/analytics.md): Read Tool Use data from the terminal — terminal commands and MCP tool calls
- [Exports](https://docs.getunbound.ai/cli/exports.md): Export Logs, Tasks, Users and Tool Use data as CSV from the terminal
- [Tool Policies](https://docs.getunbound.ai/policies/tool-policies.md): Monitor and control terminal commands and MCP tool calls made by AI coding tools
- [Security Policies](https://docs.getunbound.ai/policies/security-policies.md): Protect sensitive data with guardrails that detect, redact, or block PII, secrets, and restricted content
- [Model Policies](https://docs.getunbound.ai/policies/model-policies.md): Control which AI models are available to users in your organization
- [Cost Policies](https://docs.getunbound.ai/policies/cost-policies.md): Set budgets, spending limits, and usage controls to manage AI costs across your organization
- [Analytics & Reporting](https://docs.getunbound.ai/analytics.md): Understand agent activity, developer productivity, and AI usage across your organization
- [Chat Completions API](https://docs.getunbound.ai/integrations/api-reference.md): OpenAI-compatible chat completions endpoint for routing LLM calls through the Unbound gateway
- [List Models](https://docs.getunbound.ai/integrations/api-models.md): Retrieve available models from the Unbound gateway
- [Tool Policy Hooks (Inbound `/v1/hooks/pretool`)](https://docs.getunbound.ai/integrations/api-tool-policy-hooks.md): Enforce tool policies on agent tool calls before execution. Inbound endpoint — your agent calls the gateway, not the other way around.
- [Python SDK Integration](https://docs.getunbound.ai/integrations/python-sdk.md)
- [Cursor](https://docs.getunbound.ai/integrations/cursor-integration.md)
- [Claude Code](https://docs.getunbound.ai/integrations/claude-code-integration.md): Learn how to install and configure Claude Code for secure AI-powered coding assistance
- [Codex](https://docs.getunbound.ai/integrations/codex-integration.md)
- [Gemini CLI](https://docs.getunbound.ai/integrations/gemini-cli-integration.md)
- [GitHub Copilot](https://docs.getunbound.ai/integrations/copilot-integration.md)
- [Augment Code](https://docs.getunbound.ai/integrations/augment-integration.md)
- [Cowork](https://docs.getunbound.ai/integrations/cowork-integration.md): Stream Claude Cowork telemetry through Unbound for organization-wide observability, cost tracking, and policy enforcement
- [Roo Code](https://docs.getunbound.ai/integrations/roo-code-integration.md): Learn how to configure Roo Code to use Unbound Security AI Gateway for secure AI-powered coding
- [Cline](https://docs.getunbound.ai/integrations/cline-integration.md): Learn how to configure Cline to use Unbound Security AI Gateway
- [Kilo Code](https://docs.getunbound.ai/integrations/kilo-integration.md): Learn how to configure Kilo Code to use Unbound Security AI Gateway
- [Connect MDM Provider](https://docs.getunbound.ai/mdm-integrations/overview.md): Streamline AI tool deployments across your organization
- [Deploy AI Tools via MDM](https://docs.getunbound.ai/mdm-integrations/deploy-ai-tools.md): MDM deployment scripts to install and configure AI coding tools across managed devices
- [Tamper Resistance](https://docs.getunbound.ai/mdm-integrations/tamper-resistance.md): Keep Unbound enforcement active on every device using managed settings
- [Slack](https://docs.getunbound.ai/integrations/slack.md): Connect Slack to enable interactive approval workflows for tool policies
- [Webhooks](https://docs.getunbound.ai/integrations/webhooks.md): Receive HTTP notifications at your own URL for subscribed events
- [Support & Troubleshooting](https://docs.getunbound.ai/support/overview.md): Find answers to common questions and solutions for troubleshooting your Unbound setup
- [How to Find Your Unbound API Key](https://docs.getunbound.ai/support/api-keys/finding-your-api-key.md): Step-by-step guide to finding, creating, and managing your Unbound API key for Claude Code, Roo Code, Cursor, and other tools
- [Fixing API Key Not Working or Invalid Key Errors](https://docs.getunbound.ai/support/api-keys/troubleshooting-api-keys.md): Troubleshooting guide for when your Unbound API key is rejected, shows as invalid, or fails to connect in Claude Code, Roo Code, or other tools
- [Troubleshooting Login and Authentication Errors](https://docs.getunbound.ai/support/authentication/login-and-sso-errors.md): How to fix common login issues including SSO errors, Okta provisioning, email domain changes, and authentication failures on Unbound
- [Understanding Credits, Usage, and Budget Management](https://docs.getunbound.ai/support/billing/credits-usage-and-budgets.md): How credits work, when they reset, how to view usage, set budgets, and manage billing on Unbound
- [Usage Not Showing Up](https://docs.getunbound.ai/support/troubleshooting/usage-not-showing-up.md): Diagnose and fix Claude Code usage data not appearing in the Unbound dashboard. Written so your AI coding agent can run the checks and fixes for you.
- [Claude Code CLI Troubleshooting](https://docs.getunbound.ai/support/troubleshooting/claude-code-errors.md): Fix common Claude Code CLI errors including authentication failures, SSL certificate issues, and connection problems
- [Roo Code Integration Troubleshooting](https://docs.getunbound.ai/support/troubleshooting/roo-code-errors.md): Fix common Roo Code errors including invalid API key, missing unbound provider, and connection issues
- [Resolving Model Not Supported and Token Limit Errors](https://docs.getunbound.ai/support/troubleshooting/model-and-token-errors.md): Fix model not supported errors, enable models for your organization, and handle token limit exceeded errors
- [CLI Path Conflicts](https://docs.getunbound.ai/support/troubleshooting/cli-path-errors.md): Fix conflicts when another program shadows the unbound command
- [](https://docs.getunbound.ai/index.md)
- [Andrej Karpathy's LLM Council](https://docs.getunbound.ai/integrations/llm-council-integration.md): Learn how to set up LLM Council with Unbound for multi-model AI deliberation
- [OpenClaw](https://docs.getunbound.ai/integrations/openclaw-integration.md): Enforce tool policies and route LLM calls through the Unbound AI Gateway for OpenClaw agents
- [Unbound Claude Code for Windows](https://docs.getunbound.ai/integrations/unbound-claude-code-windows.md): Install and configure Unbound Claude Code on Windows for secure AI-powered coding assistance
- [Cowork Starting Policies](https://docs.getunbound.ai/playbook/cowork-starting-policies.md): The day-one policy pack for Claude Cowork — protect the data in prompts and draw the line on file, shell, and connector actions for general knowledge work
- [Onboarding Playbook](https://docs.getunbound.ai/playbook/introduction.md): A guided tour of the platform — what each part does, and how to get value in your first hour
- [Tool Policy Examples](https://docs.getunbound.ai/playbook/policy-examples.md): Ready-to-use Tool Policy examples with a prompt you can give your agent to see each one fire
- [Recommended Starting Policies](https://docs.getunbound.ai/playbook/recommended-starting-policies.md): The day-one policy pack for AI coding agents — stop the catastrophic handful, audit the rest, tune from your own traffic
- [Threat Model](https://docs.getunbound.ai/playbook/threat-model.md): The day-one policy pack mapped to the threats it actually defends against — the one-pager you can show your security team
- [What Each Default Protects](https://docs.getunbound.ai/playbook/what-defaults-protect.md): Every default policy mapped to the threat it stops, and why it blocks, warns, or audits

## OpenAPI Specs

- [openapi](https://docs.getunbound.ai/api-reference/openapi.json)