Sold by: Jentic
Deployed on AWS
Self-hosted execution layer that lets AI agents call any public or private API without ever seeing your credentials.
Overview
Jentic One:
Secure API Execution for AI Agents Jentic One is a self-hosted container that lets your AI agents call real APIs without ever seeing your credentials. Deploy once, connect to APIs from the Jentic API Directory or upload your own, and let agents act on external systems under rules you set, with secrets that stay encrypted and out of the agent's reach.
The Problem
Connecting AI agents to live APIs introduces risks that traditional API gateways were never built for. Credentials leak into prompts, logs, and context windows. An agent with a key can do anything that key can do. And after the fact, you often can't see what the agent actually did. Managing auth across dozens of APIs turns into sprawling, fragile plumbing.
How Jentic One Works
- Jentic One sits between your AI agent and the target APIs it needs to call. When an agent needs to interact with an external service, Jentic One handles authentication and execution on the agent's behalf:
- Install once - Deploy the Jentic One container in your own environment. Agents connect to it as clients from wherever they run, never on the instance that stores your keys, so a local process can't read them directly.
- Add any API from the Jentic API Directory - Browse available integrations and connect the services your agents need. Configuration is centralized in a single instance.
- Encrypted credential storage - Store each credential once, encrypted, within your own Jentic One instance. Credentials are injected at execution time and never enter the agent's prompt, logs, or context.
- Permission scoping - Define what each agent is allowed to do. Writes are never allowed by default, so agents start with read-only access. You explicitly grant write permissions where needed. How granular this gets depends on the API.
Key Benefits
- Credential Isolation for AI Workflows - Your API keys, tokens, and secrets are stored encrypted and injected only at the moment of execution. They are never passed to the agent itself, eliminating the risk of credential leakage through prompt injection, logging, or unintended context sharing.
- Default-Deny Write Access - Every API connection starts in a read-only mode. Write operations must be explicitly enabled, giving you a safety net against unintended modifications by autonomous agents.
- Centralized API Management Every agent draws from one governed toolkit of API connections, instead of each carrying its own keys and config. Add, remove, or update a connection once, and the change applies to every agent that uses it, with no credentials scattered across workflows to hunt down or revoke.
- Every Call Logged Jentic One records every API call an agent makes, on your own instance. You get an audit trail of exactly what each agent did, which service, which operation, allowed or denied, rather than guessing after the fact.
Who Is Jentic One For?
- AI engineering teams building agents that need to call external APIs as part of automated workflows
- Platform teams responsible for securing and governing how AI agents interact with production services
- Developers prototyping agentic applications who need a fast, secure way to connect agents to real APIs without building custom authentication plumbing
Getting Started
Jentic One is available as a container image through AWS Marketplace. Deploy it in your environment, connect your first API from the Jentic API Directory, configure permission scoping, and every call your agents make runs under your rules, logged on your instance.
For enterprise pricing, volume discounts, or custom terms, contact us at liam@jentic.com for a private offer.
Visit the Jentic API Directory to explore available integrations and learn more about how Jentic One fits into your AI agent architecture
Highlights
- Agents never see your credentials: Jentic One lets AI agents call any public or private API while your keys stay encrypted on your own self-hosted instance, injected only at execution time. They never reach the agent's prompt, logs, or context, so a leaked prompt can't leak a credential
- You set the rules, and see what agents did. Scope each AI agent to the operations it needs, with write access denied by default, so nothing acts beyond what you allow. Every call is logged on your instance, giving you an audit trail of exactly which agent called which API, and whether it was allowed or denied.
- One connection path for every API. Install Jentic One once and connect any API from the Jentic API Directory, with no custom integration to build for each service. Each credential is stored once, so onboarding a new API for your agents is configuration, not engineering.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
Helm chart — Kubernetes/EKS (bundled PostgreSQL by default)
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
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/12 months |
|---|---|---|
Users | Number of Users allowed | $20,000.00 |
Executions | Number of Executions | $0.00 |
Dimensions summary
This contract prices along two separate usage dimensions. You pay for the number of Users allowed and, independently, for the number of Executions. Users measures how many people or agent identities can access the execution layer. Executions counts the API calls your agents run through it. Both dimensions bill on a usage basis under a contract commitment. They scale independently, so you size each one to fit your team's headcount and its actual call volume. Together they set the capacity of your Jentic One deployment.
Top-of-mind questions for buyers
A User is any identity that can access the execution layer. This covers people and agent identities alike. Each registered agent connects as its own client with its own identity on your instance. Every distinct identity you register counts toward your User allowance.
An Execution is a single API call your agent runs through the layer. Each call to a public or private API — whether allowed or denied by rule — is brokered and logged on your instance. The Executions dimension meters this call volume, separate from how many Users you have.
The two bill independently and both appear on the same invoice. Users scales with your team headcount and registered agent identities. Executions scales with API call volume. Heavy, high-frequency agent traffic pushes the Executions charge up, while adding people or agents raises the Users charge.
jentic.com+1
Helpful?
Vendor refund policy
Get in touch: support@jentic.com
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
Helm chart — Kubernetes/EKS (bundled PostgreSQL by default)
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
Version 0.38.2
Additional details
Usage instructions
Jentic One deploys on Amazon EKS via the Helm delivery option. All secrets (encryption keyset, JWT secret, DB passwords) are generated on first install and reused on upgrades - zero-touch. A bundled PostgreSQL runs in-cluster by default; external RDS is supported.
Full docs: https://github.com/jentic/jentic-one/blob/main/docs/installation/aws-marketplace.md
PREREQUISITES
-
An EKS cluster (Kubernetes 1.29+), plus: aws CLI, kubectl, helm >= 3.8, eksctl.
-
Persistent storage. Fresh EKS clusters lack the EBS CSI driver and a default StorageClass; the bundled PostgreSQL needs both. Skip if you already have a default StorageClass.
eksctl create iamserviceaccount --name ebs-csi-controller-sa --namespace kube-system --cluster <cluster> --region <region> --role-name <cluster>-ebs-csi-role --role-only --attach-policy-arn arn:aws:iam::aws:policy/service-role/AmazonEBSCSIDriverPolicy --approve
eksctl create addon --cluster <cluster> --region <region> --name aws-ebs-csi-driver --service-account-role-arn arn:aws:iam::<account-id>:role/<cluster>-ebs-csi-role
kubectl annotate storageclass gp2 storageclass.kubernetes.io/is-default-class=true
- An IAM-enabled service account (IRSA) - the pods verify your Marketplace entitlement through it. The name must match your Launch page (default: jentic-one):
eksctl utils associate-iam-oidc-provider --cluster <cluster> --region <region> --approve
eksctl create iamserviceaccount --name jentic-one --namespace jentic-one --cluster <cluster> --region <region> --attach-policy-arn arn:aws:iam::aws:policy/AWSMarketplaceMeteringRegisterUsage --attach-policy-arn arn:aws:iam::aws:policy/service-role/AWSLicenseManagerConsumptionPolicy --approve
INSTALL
Use the commands from your Launch page; they follow this shape:
aws ecr get-login-password --region us-east-1 | helm registry login --username AWS --password-stdin 709825985650.dkr.ecr.us-east-1.amazonaws.com
helm install jentic-one oci://709825985650.dkr.ecr.us-east-1.amazonaws.com/jentic/charts/jentic-one --version <version> --namespace jentic-one --create-namespace --set global.serviceAccount.name=jentic-one --set global.awsmp.licenseSecret=<from-launch-page>
No other configuration is needed at install time.
POST-INSTALL (required before agents can connect)
Set the canonical base URL to the exact URL your agents will reach the app at (your ingress URL). Token exchange compares it byte-for-byte with the --url agents register with:
helm upgrade jentic-one oci://709825985650.dkr.ecr.us-east-1.amazonaws.com/jentic/charts/jentic-one --version <version> -n jentic-one --reuse-values --set app.extraEnv.JENTIC__AUTH__CANONICAL_BASE_URL=https://jentic.example.com
VERIFY
kubectl -n jentic-one get pods (app, broker, postgresql all Running) kubectl -n jentic-one port-forward svc/jentic-one-app 8000:8000 curl -s http://localhost:8000/health
Open <your URL>/app to create the first admin user, then connect an agent: jentic register --url <app URL> --broker-url <broker URL>. Expose the broker Service (port 8000 in-cluster) alongside the app.
EXTERNAL DATABASE (optional)
To use RDS/Aurora PostgreSQL instead (explicit passwords override generated ones): --set postgresql.enabled=false --set global.postgresql.enabled=false, then for each of global.databases.registry, .control and .admin set .host=<endpoint> and .password=<...>. Create the three roles/schemas on the instance first.
UPGRADES AND REMOVAL
Upgrade with helm upgrade --reset-values plus your --set overrides (--reuse-values keeps the old chart's image tag - avoid). Generated secrets are preserved. helm uninstall keeps the jentic-one-app-secrets Secret so credentials survive reinstall; delete the namespace to remove everything.
ENTITLEMENT
The app verifies your Marketplace license at runtime via the IRSA service account. If the check fails (e.g. expired contract) the API 503s after a grace period (health endpoints stay up); restoring the subscription restores service without reinstalling.
Support
Vendor support
For support with Jentic One, email the Jentic team at support@jentic.com . Include your deployment details (Docker or Python, and your version) and a description of the issue so the team can help quickly.
For Guided Demos contact: liam@jentic.com For Enterprise support contact: liam@jentic.com
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
Jentic API Scorecard measures the AI-readiness, quality, and operational maturity of your APIs. It analyzes structural compliance, developer experience, AI interpretability, agent usability, security posture, and discoverability to generate a clear readiness score and actionable recommendations. This early-access version includes guided onboarding and requires manual activation by the Jentic team.
StrongestLayer AI Email Security Platform is an AI-native email security platform that uses LLM-powered threat reasoning to detect sophisticated phishing, BEC, and AI-generated attacks that bypass legacy gateways. Deploys via API in minutes with no MX changes. Includes AI Advisor for real-time employee coaching and integrated human risk management.
Purple AI Model Context Protocol (MCP) Server provides secure, seamless integration between the Singularity Platform and any AI framework or large language model. Acting as a universal translator and intelligence hub, it empowers developers and partners to build custom agentic AI experiences powered by the full context and analytics of the SentinelOne platform. The open-source Purple AI MCP Server is available today on GitHub and will also be deployable as an EKS and through Amazon Bedrock, using Agent Core. Users will need to have an active deployment of SentinelOne console and be able to obtain the SentinelOne Singularity Console token and url to be able to deploy and use the Purple AI MCP server.
Smarter automation starts with better data. NodeZero MCP Server plugs exploitability intelligence into your existing AI ecosystem. Now your tools can prioritize, orchestrate, and validate based on attack paths proven to be exploitable, not guesswork.
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.