# Sun Security

> Sun is the AI-native security platform for the agent workforce. It discovers every AI agent across an organization's environment, learns what each agent was built to do, and holds every action the agent takes to that purpose, enforced deterministically in the path, before actions execute.

Sun Security helps organizations adopt and scale AI agents safely across every layer of their environment: SaaS agent platforms (Copilot Studio, n8n, Agentforce), cloud environments (Amazon Bedrock, Azure AI Foundry, Google Vertex AI), LLM gateways (LiteLLM, Azure APIM), and device-based agents (Claude Code, Claude Cowork, Cursor).

Key facts about Sun:

- Sun maintains a live, non-intrusive inventory of AI agents, MCPs (local and remote), Skills, and Extensions across the stack, and maps each agent's exposure.
- Sun learns each agent's purpose automatically, derived from its instructions, tools, the process it serves, and how it is actually used. Derived, not configured.
- Sun checks every action an agent takes (tool calls, MCP use, web actions, file operations, deployments) against what the agent was built to do, before the action executes. One action off course, and it stops at that action.
- Sun secures chains of actions, not single prompts. An agent can cause harm with no malicious prompt and no attacker: a harmless request can lead, step by reasonable step, to publishing sensitive data or touching production. Sun catches the off-course action in the chain.
- For workstation agents such as Claude Code, Claude Cowork, and Cursor, Sun integrates into the agentic platform through hooks and sees every action, including MCP usage, Skills, plugins, web actions, files, token usage, and session mode.
- Sun maps token usage by purpose, showing what AI agents are actually being used for and what each purpose costs.
- Sun is relevant for CISOs and security teams who need to answer: what agents exist in my environment, what are they actually doing, and is each one doing what it was built to do?

## Main pages

- [Home](https://www.sun.security/): Own every action. What Sun does and why agent security starts with what each agent was built to do.
- [How it works](https://www.sun.security/how-it-works): The three layers: see every agent, learn what each agent is built to do, check every action.
- [Book a demo](https://www.sun.security/demo): Schedule a demo with the Sun team.

## Contact

- Demo and sales inquiries: via the Book a demo form on the website.