> For the complete documentation index, see [llms.txt](https://ai-security-docs.akto.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-security-docs.akto.io/agentic-guardrails.md).

# Agentic Guardrails

- [Get Started](https://ai-security-docs.akto.io/agentic-guardrails/overview.md): Real-time guardrail protection for AI agents and MCP endpoints
- [MCP Proxy](https://ai-security-docs.akto.io/agentic-guardrails/overview/akto-mcp-proxy.md)
- [AI Agent Proxy](https://ai-security-docs.akto.io/agentic-guardrails/overview/akto-agent-proxy.md)
- [AI LLM Proxy](https://ai-security-docs.akto.io/agentic-guardrails/overview/ai-llm-proxy.md)
- [Guardrails as API](https://ai-security-docs.akto.io/agentic-guardrails/overview/guardrails-api.md): Use the Akto Guardrails HTTP API to inspect and ingest AI agent traffic directly
- [Concepts](https://ai-security-docs.akto.io/agentic-guardrails/concepts.md)
- [Agent Guard](https://ai-security-docs.akto.io/agentic-guardrails/concepts/agent-guard.md)
- [Schema Conformance](https://ai-security-docs.akto.io/agentic-guardrails/concepts/schema-conformance.md)
- [Guardrail Actors](https://ai-security-docs.akto.io/agentic-guardrails/concepts/threat-actors.md)
- [Threat Dashboard](https://ai-security-docs.akto.io/agentic-guardrails/concepts/threat-dashboard.md)
- [Guardrail Activity](https://ai-security-docs.akto.io/agentic-guardrails/concepts/guardrail-activity.md)
- [Dynamic Agent Rate Limiting](https://ai-security-docs.akto.io/agentic-guardrails/concepts/api-rate-limit.md): Intelligent rate limiting and abuse prevention for AI agents and agentic systems.
- [Guardrail Schema](https://ai-security-docs.akto.io/agentic-guardrails/concepts/guardrail-schema.md)
- [Guardrail Policy](https://ai-security-docs.akto.io/agentic-guardrails/concepts/threat-policy.md)
- [Successful Exploits](https://ai-security-docs.akto.io/agentic-guardrails/concepts/successful-exploits.md)
- [Remediation Steps](https://ai-security-docs.akto.io/agentic-guardrails/concepts/remediation-steps.md)
- [For Agent Protection Issues](https://ai-security-docs.akto.io/agentic-guardrails/concepts/remediation-steps/for-agent-protection-issues.md)
- [For MCP Protection Issues](https://ai-security-docs.akto.io/agentic-guardrails/concepts/remediation-steps/for-mcp-protection-issues.md)
- [How To](https://ai-security-docs.akto.io/agentic-guardrails/how-to.md)
- [Create Guardrail Policies](https://ai-security-docs.akto.io/agentic-guardrails/how-to/create-guardrail-policies.md)
- [Enable or Disable Guardrails](https://ai-security-docs.akto.io/agentic-guardrails/how-to/enable-or-disable-guardrails.md)
- [Manage Guardrail Policies](https://ai-security-docs.akto.io/agentic-guardrails/how-to/manage-guardrail-policies.md)
- [Access A Specific Guardrail Actor](https://ai-security-docs.akto.io/agentic-guardrails/how-to/access-a-specific-guardrail-actor.md)
- [Guardrail Activity Detailed View](https://ai-security-docs.akto.io/agentic-guardrails/how-to/guardrail-activity-detailed-view.md)
- [Take Action on Guardrails Events](https://ai-security-docs.akto.io/agentic-guardrails/how-to/take-action-on-guardrails-events.md)
- [Create Internal Workflow Item](https://ai-security-docs.akto.io/agentic-guardrails/how-to/create-internal-workflow-item.md)
- [Understand Agentic Components](https://ai-security-docs.akto.io/agentic-guardrails/how-to/understand-agentic-components.md)
- [Export Visualisation and Report](https://ai-security-docs.akto.io/agentic-guardrails/how-to/export-visualisation-and-report.md)
- [Export Activity to Custom Webhook](https://ai-security-docs.akto.io/agentic-guardrails/how-to/export-activity-to-custom-webhook.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-security-docs.akto.io/agentic-guardrails.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.