Jentic APIs for AI Agents
Identity AuthAuthorizationSecrets ManagementOfficial Vendor DocumentsBearer tokenAgent Ready
For Agents
APIs2 in catalogue
Endpoints178 indexed
AuthBearer token — 1 credential for all 2 APIs
ProvenanceOfficial OpenAPI documents
An agent operator can register agents, store upstream credentials, and write permission rule sets through the Control Plane, then have the agent forward authenticated calls to any upstream API through the Broker without ever holding the secret. The two APIs let an agent act within deliberate, auditable bounds set by its operator.
Jentic One separates deciding what an agent may call from executing the call: the Control Plane holds credentials, permission rules, agent identities, and the audit log, while the Broker forwards the authenticated request with the secret injected at the proxy. That split lets an operator bound an agent's reach centrally and route every outbound call through one auditable egress point, rather than embedding keys and access logic in agent code.
Jentic API Catalog
2 APIs across 2 product groups. All share one credential.
Which Jentic API should I use?
| I want to... | Use |
|---|---|
| Decide what an agent is allowed to call and store its credentials | Jentic One Control Plane API |
| Make an authenticated call to an upstream API without the agent holding the secret | Jentic One Broker API |
| Review what an agent actually did and under which credential | Jentic One Control Plane API |
Install Jentic One Beta
Connect the Jentic APIs to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Jentic APIs, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fjentic.com" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fjentic.com" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Once connected, ask your agent something like: “govern and proxy an AI agent's upstream API calls with Jentic One”.
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Building agent API governance by hand means standing up credential storage, a rules engine, agent registration, an audit trail, and a credential-injecting proxy yourself. With Jentic One you install once, import the Control Plane and Broker from the API Directory, store the bearer token once, and your agent calls the operations it needs.
Permission scoping
The Control Plane carries agent and credential ids in the URL path and the Broker splits forwarding by HTTP method, so a rule can pin an agent to specific records and allow read forwarding while withholding destructive forwards. You choose the operation set, so an agent gets exactly the reach you grant and nothing more.
Credential isolation
Your bearer tokens and the upstream credentials the Broker injects are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context, and running the agent on a separate machine keeps it from reading the stored keys.
Intent-based discovery
Agents search Jentic by intent such as 'write a permission rule set' or 'call an upstream API with injected credentials', and Jentic returns the matching Control Plane or Broker operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
FAQs
Specific to using Jentic APIs through Jentic.
How do the Jentic One Control Plane and Broker APIs fit together?
They split the work of making an agent's API calls governable. The Control Plane decides what is allowed: it stores credentials, writes permission rule sets, registers agents, and keeps the audit log. The Broker executes: it forwards the authenticated request to the upstream API with the stored credential injected at the proxy. The Control Plane configures and records, the Broker runs the call, so an operator can bound an agent's reach without putting access logic or secrets in agent code.
Does one credential work across both Jentic One APIs?
Yes, within one instance. Both APIs authenticate the caller with a bearer token, and a token issued for a Jentic One instance reaches both the Control Plane and the Broker on that instance. The upstream credentials the Broker injects are separate: they are stored by the Control Plane and are never returned to callers in plaintext.
Which Jentic One API should an agent call for a given task?
Use the Control Plane to administer access: register agents, store or rotate credentials, write permission rules, and read the audit log. Use the Broker to make an actual outbound call: forward a request to an upstream API and get the response back. A full workflow usually starts in the Control Plane to set up access and then uses the Broker to execute within it.
Where does Jentic One run, and what does it not do?
Jentic One is self-hosted: you install it and run it on your own infrastructure. The setup keeps the agent on a machine separate from the instance so the agent cannot read stored credentials directly. It governs and forwards API calls; it does not handle end-user login or SSO, host end-user data, or run the agent's own workloads.
Do I need a separate MCP server to use these APIs with an agent?
No separate per-API MCP server is needed. You install Jentic One and import the API you need, and your agent reaches it through Jentic One's own interface, available as a command-line tool or an MCP server. Store your bearer token once and operations are discovered on demand by intent, so no extra per-API tool definitions sit in the agent's context.
BOOK A DEMO
Start Connecting APIs to Your AI Agents
Browse thousands of APIs and connect them all to your agent with Jentic One. One layer, one credential — every API your agent needs.