Sold by: Marquor
Deployed on AWS
Every consequential agent action becomes an Ed25519-signed, hash-chained receipt that verifies offline, with no call back to Marquor. Payload-free: declared metadata, never content.
Overview
Marquor is an enforcement and evidence layer for AI agents.
Every consequential action an agent takes, allowed and denied alike, is minted as an Ed25519-signed, hash-chained receipt. The receipt verifies offline, with no call back to Marquor. Because the chain is hashed, a retroactive edit or deletion is detectable. A third party can check your evidence without trusting us.
Marquor is payload-free by construction. Prompts, files and transaction bodies are never collected. It evaluates declared metadata only: spend bands rather than amounts, digests rather than payees. Because the receipt carries no content, it crosses an organisational boundary intact, with nothing to negotiate away first.
The decision behind each receipt is made at the agent-to-tool boundary, in real time, against verified identity and signed policy. It is deterministic. No LLM sits in the decision path, so the same inputs give the same answer, in microseconds on CPU.
ARA, Agent Risk and Adjudication Analytics, runs after authorization and off the hot path: no synchronous call in your customer flow, no added latency. It classifies the actor behind an action as human, legitimate agent, hijacked agent or malicious bot, with probabilities and a liability recommendation. It abstains when it is not sure rather than guessing, and routes flagged cases by calibrated confidence to auto-clear, assist, or human review. Alongside it, Detect senses behaviour against per-agent baselines across fourteen detector families, including treating an agent going silent as an alarm.
Both engines observe and recommend. Neither blocks. Enforcement remains the gateway's signed clearance, so an analytics result can never quietly change what an agent may do. The only containment that fires automatically is the gateway's reversible throttle.
This listing runs a 15-day evaluation in monitor mode inside your own AWS account: signed receipts from day one, nothing denied until you choose to enforce. Marquor has passed the AWS Foundational Technical Review and completed an AWS Well-Architected Framework Review.
Highlights
- Every agent decision, allow and deny alike, becomes an Ed25519-signed, hash-chained receipt that a third party can verify offline, with no call back to Marquor and without trusting us.
- Payload-free by construction: prompts, files and transaction bodies are never collected. Declared metadata only, spend bands rather than amounts, digests rather than payees.
- ARA classifies each actor as human, legitimate agent, hijacked agent or malicious bot, with a liability recommendation. Off the hot path, zero added latency. It recommends; it never blocks.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
Kubernetes (Amazon EKS) - Helm
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
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.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Vendor refund policy
Marquor charges no fees for this product, so no refunds arise. It provides a 15-day monitor-mode evaluation from first deployment: enforcement stays disabled and the entitlement expires at the end of that period. Extensions and paid editions are available on request. AWS infrastructure charges for running the gateway in your own AWS account are billed by AWS and are outside Marquor's control. Contact support@marquor.io for evaluation support or to request an extension.
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.
Delivery details
Kubernetes (Amazon EKS) - Helm
Supported services: Learn more
- Amazon EKS
- Amazon EKS Anywhere
Helm chart
Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.
Version release notes
Bump to gateway 1.2.0 (ledger credential-provider build, main b06f834). Chart 0.5.0: throughput-limit defaults baked in - a 6000 rpm per-caller-IP rate cap and a 256 in-flight cap replace the binary defaults (120/64); a customer's own extraEnv still overrides. Single-writer ledger, fail-closed loaders, payload-free evidence unchanged. Multi-arch (x86-64 and Graviton) on EKS / EKS Anywhere / self-managed Kubernetes.
Additional details
Usage instructions
-
Prerequisites. A Kubernetes cluster (EKS 1.25+ recommended), an OIDC issuer your agents authenticate against, and a StorageClass supporting ReadWriteOnce.
-
Provide four OAD documents. identity.yaml (issuer/audience/JWKS; PUBLIC keys only), policy.yaml (the global default-deny floor), and per agent a dossier manifest plus a clearance allow-list. Every loader is fail-closed: the gateway refuses to boot on anything invalid, and a verified-but-uncertified caller gets deny-all.
-
Install. Set upstreamUrl to your MCP server and supply the OAD documents. The chart mounts them read-only from ConfigMaps and the admin token from a Secret. The chart ships with inert placeholder defaults so it renders out of the box: an unconfigured install denies everything and reaches nothing. Replace upstreamUrl and the identity document before expecting it to serve traffic.
-
Two constraints the chart enforces by refusing to install:
- Exactly one replica. The gateway is single-writer: one Ed25519 signing key, one hash-chained traces.jsonl, one ReadWriteOnce volume. Two replicas fork the chain into branches signed by different keys, destroying tamper-evidence silently. The Deployment strategy is Recreate, never RollingUpdate.
- Persistent storage is required. /data holds the signing key and the ledger. Losing it restarts the chain under a new key.
-
Verify. GET /healthz returns {"status":"ok"}. Point your agents at the gateway's /mcp endpoint - no agent code changes are required. Start in monitor mode, review the receipts, then switch to enforce.
Support
Vendor support
Marquor provides technical support for product onboarding, deployment, configuration, integrations, policy setup, runtime enforcement, and troubleshooting.
AWS infrastructure support
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.
Similar products
AI Runtime Security (also known as Prisma AIRS) is an adaptive, purpose-built solution that discovers, protects, and defends every component in the AI ecosystem, applications, models, and data from AI-specific and foundational network threats.
It stops evolving and zero-day threats, prevents data leakage from AI models and apps and safeguards models from misuse and attacks. This is done by combining continuous runtime threat analysis of AI apps, models, and data sets with AI-powered security to detect and stop attackers in real time. Security operations are streamlined because they are delivered as part of a unified security platform, eliminating the need for point products for AI.
Arcade.dev is the industry's first MCP runtime enabling AI to take secure, real-world actions. As the MCP runtime, Arcade is uniquely able to deliver secure agent authorization, high-accuracy tools, and centralized governance for multi-user AI agents at scale.
PhaseV ClinOps Optimizer helps sponsors run faster, leaner, and more successful trials by transforming site selection and operational oversight into a data-driven process. End-to-end site selection optimization delivered within your AWS Cloud.
Contrast Runtime Application Security Platform equips developers, AppSec and SecOps teams with one platform that proactively identifies runtime application vulnerabilities in pre- and post production in order to protect and defend applications and APIs against evolving threats. Armed with the right knowledge, security teams can identify exploitable issues, detect incidents in real-time, and block attacks. This enables them to achieve a more accurate and actionable security posture than they could with traditional network and endpoint security tools.
Customer reviews
No customer reviews yet
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.