Netzilo is AIDR (AI Detection & Response) for AI agents, governing what your agents do (tool calls, data access, network activity), not just what a model says. It detects and stops prompt injection, tool poisoning, and multi-step data exfiltration in real time across Amazon Bedrock AgentCore, MCP, and A2A, and streams enriched events to your SIEM. Deploy cloud or self-hosted, agentless or with the Netzilo Client, for AI agent security, runtime governance, and agentic AI observability.
Overview Netzilo is the runtime security and governance plane for the agentic workforce. As enterprises deploy AI agents on Amazon Bedrock AgentCore and connect them to tools over MCP and A2A, those agents gain the ability to read files, call APIs, move data, and act across systems at machine speed, largely invisible to a security stack built for human users. Guardrails supervise what a model says; Netzilo governs what an agent does. It gives security and platform teams the visibility, control, and evidence to adopt agentic AI safely. How it works AI Detection & Response (AIDR) records every action every agent takes: tool and skill calls, file reads, network requests, LLM calls, and process activity, as a live, queryable Behavior Graph. Deterministic, human-readable policies (Governance-as-Code) query that graph at runtime to correlate the multi-step chains that single-event tools miss. Three engines work together: a Static Scanner (PII, secrets, known-bad patterns), a Behavior Scanner (graph-aware detection of prompt injection, tool poisoning, privilege escalation, and data exfiltration), and a Kill-Switch that isolates or terminates a compromised agent in under a second, with no human in the millisecond loop. Key capabilities See - discover shadow AI, unmanaged MCP servers, and agent activity across your environment Detect - catch prompt injection, tool poisoning, and multi-stage exfiltration chains in real time Stop - enforce deterministic policy and kill-switch response at the tool-call level Prove - stream enriched, correlated events to your SIEM and security data lake for audit-ready evidence Built for AWS AIDR runs inline with Amazon Bedrock AgentCore agents and the MCP servers they call, inspecting and governing every action before it leaves your VPC. It streams enriched events (OpenTelemetry / OCSF) to your SIEM and Amazon Security Lake, authenticates against your identity provider (Okta, Entra ID), and can run fully self-hosted in your AWS account or as a managed service, with no enterprise data routed through third-party infrastructure. Deploy agentlessly via an agent plugin or browser extension in minutes, or with the Netzilo Client for OS-level and arbitrary-agent coverage. Who it's for Security, platform, and AI teams standardizing agentic AI on AWS, especially regulated enterprises in financial services, healthcare, and technology that need runtime governance, audit-ready evidence, and assurance that autonomous agents stay within policy.
Highlights
Runtime AI agent security - govern what your AI agents do (tool calls, data, network) across Amazon Bedrock AgentCore and MCP, not just what the model says.
Real-time threat detection & response - stop prompt injection, tool poisoning, and data exfiltration in under a second, with runtime AI governance built in.
See every AI agent in your environment. Netzilo AIDR builds a live Behavior Graph of what each agent actually does - tool calls, file access, MCP calls, and network activity across Amazon Bedrock AgentCore - surfacing the shadow AI and unmanaged MCP servers that traditional AI agent security tools never see.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
This listing uses a single usage-based pricing dimension. You pay for active licensed users, metered by the hour. Your cost scales directly with how many users are active during each billing period. There are no tiers or fixed commitments to choose between. As you add or remove users, your billing adjusts to match actual usage. This gives you a pay-as-you-go structure tied to your active user count.
Top-of-mind questions for buyers
What counts as one active licensed user for billing?
A user is a team member you add to your Netzilo network to access company resources. Each person granted access counts as one licensed user. The platform meters these active users hourly, so billing reflects who has access during each hour, not total accounts created.
What happens to my cost when I add or remove users mid-period?
Because billing is metered hourly, your cost adjusts as your active user count changes. Adding a user starts charges for that user in the hours they are active. Removing a user stops charges once they are no longer active. You pay only for active licensed users each hour.
Do I commit to a set number of users, or is this pay-as-you-go?
This is a pay-as-you-go structure with no upfront commitment. You are not locked into a fixed user count or term. Charges accrue hourly based on active licensed users. As your workforce or contractor access grows or shrinks, your bill follows actual usage.
doc.netzilo.com+1
Helpful?
Vendor refund policy
All fees are non-refundable except as expressly provided in the Netzilo Terms of Service. On early termination for cause, or where Netzilo is legally required to terminate, prepaid fees are refunded on a pro-rata basis for the remainder of the paid term. Plan changes are prorated at the next billing period. For AWS Marketplace purchases, billing and any eligible refunds are processed through AWS Marketplace
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
This template deploys a complete Netzilo ZTNA server end to end on a single EC2 instance - management, signal, dashboard, identity (Zitadel), TURN/STUN relay, and database - and automatically obtains a Let's Encrypt certificate on first boot. Before running this stack, make sure your domain and Elastic IP are ready: allocate an Elastic IP, and point your domain's DNS A record at that Elastic IP, so certificate issuance succeeds when the instance starts.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
NetziloServer with AI Edge - Pay As You Go
Additional details
Usage instructions
Template components
CloudFormation template
Usage instructions
Netzilo Server - Usage Instructions
1. Before launching
Allocate an Elastic IP in this region (EC2 > Elastic IPs > Allocate); note its allocation ID (eipalloc-...).
Point your domain at that IP - create a DNS A record for your FQDN (e.g. vpn.example.com) > the Elastic IP. Do this before launch so Let's Encrypt succeeds on first boot.
Have a VPC and a public subnet (auto-assign public IP / internet gateway) to launch into.
2. Launch the stack
Launch via AWS Marketplace (the AMI ID is filled in automatically) and set the CloudFormation parameters:
Domain (FQDN) - must already resolve to your Elastic IP
Elastic IP allocation ID - the eipalloc-... from step 1
Admin email - the initial administrator login
Admin first / last name - shown in the UI
Admin password - 12+ chars incl. uppercase, lowercase, number, and symbol
Instance type - t3.large fits most deployments
VPC / Public subnet - select from the dropdowns
Allowed admin CIDR - restrict dashboard/SSH to your range (default 0.0.0.0/0)
Database mode - container (PostgreSQL on the instance) or external (Amazon RDS)
Acknowledge the IAM checkbox and create the stack.
3. First boot
At CREATE_COMPLETE, the instance provisions itself - pulling images, creating your admin account, and obtaining the Let's Encrypt certificate. Allow a few minutes after the stack finishes.
4. Access
Open CloudFormation > Outputs:
DashboardURL - https://<your-domain>; sign in with your admin email and password.
AdminCredentialsConsoleLink - credentials, also stored in SSM Parameter Store.
SessionManagerCommand - open a shell via SSM Session Manager (no SSH key needed).
5. Administration
Shell: use SessionManagerCommand (aws ssm start-session --target <instance-id>), or SSH if you supplied a key pair.
App & logs: under /opt/netzilo; runs as a Docker Compose stack.
Notes
DNS must resolve to the Elastic IP before launch; otherwise certificate issuance fails - fix DNS and reboot to retry.
Ports 80/443 and the TURN/STUN relay ports must be reachable (opened by the stack's security group, restricted to your admin CIDR where applicable).
Ubuntu 22.04 LTS, single instance. For production resilience, back up the EBS volume or use external database mode with RDS.
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Netzilo is AIDR (AI Detection & Response) for AI agents, governing what your agents do (tool calls, data access, network activity), not just what a model says. It detects and stops prompt injection, tool poisoning, and multi-step data exfiltration in real time across Amazon Bedrock AgentCore, MCP, and A2A, and streams enriched events to your SIEM. Deploy cloud or self-hosted, agentless or with the Netzilo Client, for AI agent security, runtime governance, and agentic AI observability.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.