Self-Hosted Deployment

Overview

Ask Akto is an AI-powered conversational assistant integrated into Akto's security platform that enables users to have real-time conversations about Agentic vulnerabilities, test results, and security insights.

Key Capabilities

  • Interactive Vulnerability Analysis: Ask questions about test results and vulnerabilities in natural language

  • Agentic and API Security Guidance: Get AI-powered remediation suggestions and security best practices

  • Test Result Analysis: Deep-dive into why tests passed/failed with AI assistance

  • Dashboard Metrics Discussion: Analyse Agentic collections, endpoints, and risk scores

  • Conversation History: Track and search through past security discussions

  • Multi-Conversation Support: Maintain separate conversation threads for different contexts

Pre-requisites

  • Docker and Docker Compose installed

  • Anthropic API Key

  • Akto API Security Dashboard running (self-hosted instance)

Deployment Setup

1

Create the Deployment Directory

Create a directory that stores the Docker Compose configuration and environment files.

The directory acts as the working location for the deployment.

2

Create Docker Compose File

Create a docker-compose.yml file with the following configuration:

The Docker Compose configuration defines two services:

  • agent-testing – runs the AI-driven Agentic engine.

  • mcp-server – provides the MCP interface used by the testing agent.

3

Create Environment Files

Two environment files configure runtime behavior for the containers.

Environment File for Agent Testing Service

Create a file named: docker-agentic-testing-dashboard.env

Environment variables

Variable
Purpose

ANTHROPIC_API_KEY

API key used for accessing Anthropic Claude models.

PORT

Port exposed by the agent-testing service. Default value: 5500.

MCP_SERVER_URL

URL used by the agent-testing service to communicate with the MCP server. Replace <YOUR_MCP_SERVER_HOST> and <YOUR_MCP_SERVER_PORT> with the MCP server host and port configured in the deployment environment.

Environment File for MCP Server

Create a file named: docker-mcp-server.env

Environment variables

Variable
Purpose

AKTO_BASE_URL

Base URL of the Akto API Security Dashboard. Replace <YOUR_AKTO_DASHBOARD_HOST> and <PORT> with the hostname and port configured in the on-prem deployment.

MCP_MODE

Deployment mode of the MCP server. Value internal is used for on-prem environments.

MCP_API_KEY

Authentication key used for MCP server access.

4

Start the Services

Expected output:

5

Verify Connectivity

You can verify that both services started successfully by checking the health endpoints.

Agent Testing Service

MCP Server

Usage

Once deployed, Ask Akto can be accessed through the Akto's Security Dashboard:

  1. Navigate to your Akto dashboard

  2. Access the Ask Akto feature section

  3. Start conversing with the agent.

Support

If you need help with the deployment:

Our team is available 24/7 to assist you with setup, troubleshooting, and best practices.

Last updated