Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
**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.
Show the rest of the publisher’s description (11 more lines)
**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
Highlighted by the publisher on AWS Marketplace.
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.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment
Plans and pricing as listed
4 listed- Users
- Users
- Users
- Users
Refund terms
As stated by the publisher on AWS Marketplace.
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
Sources
Publisher resources
2 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.