> 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/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started.md).

# Get Started

Probe your AI agents, MCP servers, and AI models with 4000+ specialized security probes. Akto identifies vulnerabilities like prompt injections, tool abuse, and privilege escalation before attackers do.

## 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: Choose Probing Approach

**Option A: Probe Existing Assets**

Already have discovered agents and MCP servers in your inventory? Start probing immediately.

→ [Red Team Existing Agentic Asset](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/red-team-existing-agentic-asset.md)

**Option B: Import New Components**

Navigate to **Quick Start** in your Akto dashboard and import the components you want to probe:

#### Import AI Agents

Probe agents from AWS Bedrock, Azure AI Foundry, Databricks, Google Vertex AI, IBM Watsonx, or custom agents.

→ [Import AI Agents](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/manual-import.md)

#### Import MCP Servers

Probe Model Context Protocol tools, resources, and prompts by connecting to SSE endpoints.

→ [Import MCP Servers](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/manual-import.md)

#### Import AI Models

Probe large language models and custom AI implementations for security vulnerabilities.

→ [Import AI Agents](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started/manual-import.md)

### Step 3: Run Security Probes

Once imported:

1. Navigate to **AI Red Teaming** in your dashboard
2. Select the components you want to probe
3. Choose from 4000+ specialized security probes
4. Click **Run Probes** to start probing

### Step 4: Review Results

After probes complete:

1. View all identified vulnerabilities
2. See detailed exploit scenarios
3. Get remediation guidance for each issue
4. Export reports for your team

## What Gets Probed

Akto probes for:

* Prompt injection attacks
* Tool permission escalation
* Data leakage vulnerabilities
* Authentication bypass
* MCP schema violations
* Supply chain risks

## Next Steps

* Set up continuous probing with [discovery agents](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-ai-discovery.md)
* Enable [Guardrails](/agentic-guardrails/overview.md) to block threats in production
* Review compliance posture against security frameworks

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