# Agentic AI Discovery

Discover and inventory all your AI agents, MCP servers, and tool integrations across your infrastructure. Akto automatically maps your agentic landscape, helping you identify shadow agents, track agent behaviors, and maintain visibility over your autonomous 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: Choose Your Discovery Method

Navigate to **Quick Start** in your Akto dashboard and select your preferred discovery method:

[**Homegrown Discovery Agents**](/akto-argus-agentic-ai-security-for-homegrown-ai/connectors.md) Deploy discovery agents to continuously monitor your infrastructure. Includes API Gateways, eBPF, Kubernetes, manual import, and MCP Recon.

### Step 3: Configure Your Discovery Agent

Follow the setup guide for your chosen method. Each connector provides step-by-step instructions for deployment.

### Step 4: View Your Inventory

Once your discovery agent is running:

1. Go to **Agentic Discovery** in your dashboard
2. See all discovered agents, MCP servers, and tools
3. Click on any component to view detailed information

## What Gets Discovered

Akto automatically identifies:

* AI agents and their endpoints
* MCP servers (tools, resources, prompts)
* Tool integrations and permissions
* Data flows and agent interactions
* Authentication patterns

## Next Steps

* Run [Red Teaming](/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-red-teaming/get-started.md) on discovered components
* Enable [Guardrails](/agentic-guardrails/overview.md) for real-time protection
* Review discovered agents for shadow or zombie components

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


---

# Agent Instructions: 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/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-ai-discovery.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.