> For clean Markdown of this page, append .md to its URL. For the complete documentation index, see https://www.superagent.sh/llms.txt.


Check what agents consume and monitor or block risky actions where agents run.

# Agent Guardrails

Context Guardrails and Runtime Guardrails are separate Superagent products that
protect different parts of an agent interaction.

| Guardrail | Control point |
| --- | --- |
| [Context Guardrails](https://www.superagent.sh/docs/products/context-guardrails) | Checks external content before an agent consumes it |
| [Runtime Guardrails](https://www.superagent.sh/docs/products/runtime-guardrails) | Monitors or blocks risky actions where an agent runs |

Both guardrails send findings into the security factory. Customer agents and
workflows act on those findings, structured agent reports return through
Superagent MCP, and Superagent retains the reports as context for later work.

## Next steps

- [Check external content with Context Guardrails](https://www.superagent.sh/docs/products/context-guardrails)
- [Monitor agent actions with Runtime Guardrails](https://www.superagent.sh/docs/products/runtime-guardrails)
- [Write and enforce runtime rules](https://www.superagent.sh/docs/products/runtime-guardrails/rules)

---
Source: https://www.superagent.sh/docs/products/agent-guardrails
Index: https://www.superagent.sh/llms.txt