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, scan results, and security insights.
Key Capabilities
Interactive Vulnerability Analysis: Ask questions about scan results and vulnerabilities in natural language
Agentic and agentic AI security Guidance: Get AI-powered remediation suggestions and security best practices
Scan Result Analysis: Deep-dive into why scans 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 Agentic AI Security Dashboard running (self-hosted instance)
Deployment Setup
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.
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 AI agent.
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
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
AKTO_BASE_URL
Base URL of the Akto Agentic AI 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.
Start the Services
Expected output:
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:
Navigate to your Akto dashboard
Access the Ask Akto feature section
Start conversing with the agent.
Support
If you need help with the deployment:
Discord Community: Join our community at discord.gg/Wpc6xVME4s
Email Support: Contact us at support@akto.io
Our team is available 24/7 to assist you with setup, troubleshooting, and best practices.
Last updated