> 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/overview.md).

# Get Started

Deploy real-time protection for your AI agents and MCP servers. Akto Guardrails blocks threats as they occur, preventing prompt injections, tool abuse, and unauthorized access before they impact your systems.

## Quick Start

### Step 1: Sign Up or Log In

1. Go to [app.akto.io](https://app.akto.io)
2. Sign up for a new account or log in to your existing account

### Step 2: Navigate to Connectors

1. Go to **Quick Start** in your Akto dashboard
2. Scroll to the **Guardrails** section
3. Choose the proxy type that matches your setup

### Step 3: Configure Your Proxy

Select and configure the appropriate protection proxy:

#### For MCP Servers

Deploy real-time protection for Model Context Protocol servers, tools, and resources.

→ [Set Up MCP Proxy](/agentic-guardrails/overview/akto-mcp-proxy.md)

**What it protects:**

* MCP tool invocations
* Resource access patterns
* Prompt handling
* Schema compliance

#### For AI Agents

Deploy real-time protection for AI agents and LLM applications.

→ [Set Up Agent Proxy](/agentic-guardrails/overview/akto-agent-proxy.md)

**What it protects:**

* Agent requests and responses
* Tool permission enforcement
* Authentication patterns
* Data leakage prevention

### Step 4: Enable Protection

Once your proxy is configured:

1. Set environment variable: `AKTO_THREAT_ENABLED=true`
2. Start routing traffic through the proxy
3. Monitor threats in **Guardrails** dashboard
4. Configure custom policies as needed

### Step 5: Monitor & Respond

From your Guardrails dashboard:

1. View real-time guardrail detection
2. See blocked attacks and patterns
3. Configure blocking rules
4. Set up alerts for critical violations

## What Gets Protected

Akto Guardrails defends against:

* Prompt injection attacks
* Tool abuse and permission escalation
* Unauthorized access attempts
* Schema violations
* Suspicious data patterns
* Known attack signatures

## Key Features

* **Real-Time Guardrails**: Identify and respond to agentic security threats as they occur
* **OWASP Core Rule Set Support**: Detect common attack patterns including XSS and SQL injection in agent interactions
* **Prompt Injection Protection**: Block malicious prompts attempting to manipulate agent behavior
* **Tool Permission Enforcement**: Prevent unauthorized tool access and permission escalation
* **Schema Conformance**: Ensure agent requests comply with expected MCP schemas
* **Geofencing**: Restrict agent component access based on geographic locations
* **IP-Based Blocking**: Block or allow traffic from specific IP addresses or CIDR ranges

## Next Steps

* [Discover your agents](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-ai-discovery.md) to get full visibility
* [Run Red Teaming Probes](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started.md) to identify vulnerabilities
* [Configure custom blocking policies for your use case](/agentic-guardrails/how-to/create-guardrail-policies.md)

Need help? Contact <support@akto.io> or use in-app Intercom.


---

# 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/overview.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.