Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the OpenLink OSDB REST API, 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.
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%2Fopenlinksw.com%2Fopenlinksw" | shStep 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%2Fopenlinksw.com%2Fopenlinksw" | 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.
What an agent can do with OpenLink OSDB REST API.
List the services available on the OSDB server
Load and unload services
Describe a service and the actions it defines
List and describe the actions of a service
Read the help text for an action
GET STARTED
Execute an action and begin or end a session
Patterns agents use OpenLink OSDB REST API for, with concrete tasks.
★ Service and Action Discovery
An agent maps what it can do by calling GET /api/v1/services for the loadable services and GET /api/v1/actions/{serviceId} for the actions each one defines. This lets it plan a task without a hard-coded list of capabilities.
List services with GET /api/v1/services, then GET /api/v1/actions/{serviceId} for their actions
Parameter-Aware Execution
Before running work, an agent reads an action's shape with GET /api/v1/actions/{serviceId}/{actionId} and then runs it with POST /api/v1/actions/{serviceId}/{actionId}/exec. Reading the definition first keeps the call well-formed.
Describe the action, then execute it with POST /api/v1/actions/{serviceId}/{actionId}/exec
Service Lifecycle
An agent brings a capability online with POST /api/v1/services and removes it afterward with the unload operation, keeping the active set tight. This is useful when only some services should be exposed for a given task.
Load the service with POST /api/v1/services and unload it when the task is done
Guided Action Help
When an action is unfamiliar, an agent reads GET /api/v1/actions/{serviceId}/{actionId}/help to learn how to use it before running anything. This lowers the chance of a malformed call.
Read the guidance with GET /api/v1/actions/{serviceId}/{actionId}/help before executing
10 endpoints — the openlink osdb rest api exposes services and the actions they define so a caller can discover what is loadable, load or unload a service, list its actions, read the help for one, and execute it.
METHOD
PATH
DESCRIPTION
/api/v1/services
List available services
/api/v1/actions/{serviceId}
List the actions of a service
/api/v1/actions/{serviceId}/{actionId}
Describe an action
/api/v1/actions/{serviceId}/{actionId}/exec
Execute an action
/api/v1/services
Load a service
/api/v1/services
List available services
/api/v1/actions/{serviceId}
List the actions of a service
/api/v1/actions/{serviceId}/{actionId}
Describe an action
/api/v1/actions/{serviceId}/{actionId}/exec
Execute an action
/api/v1/services
Load a service
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the OpenLink OSDB REST API by hand means learning its 10 operations across services, actions, and session, and handling the serviceId and actionId parameters against https://osdb.openlinksw.com/osdb. Through Jentic you install once, import the OpenLink OSDB REST API from the API Directory, and your agent calls it.
Permission scoping
Because you run Jentic One yourself, you decide which OSDB operations the agent may call. You can allow only the discovery operations that list and describe services and actions, and leave execute, load, and unload out of the allowed set unless you add them.
Credential isolation
The OpenLink OSDB REST API declares no security scheme, so there is nothing to hold or inject. Jentic calls its operations directly, and no secret ever enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent, such as 'list the services on the server' or 'execute an action', and Jentic returns the matching OSDB operation with its input schema so the agent calls the right endpoint.
Alternatives and complements available in the Jentic catalogue.
Specific to using OpenLink OSDB REST API through Jentic.
What can an AI agent do with the OpenLink OSDB REST API?
An agent can list the services on the server, load and unload them, list and describe the actions a service defines, read an action's help, and execute an action. It works as a discovery-and-execution layer over server-side capabilities.
Does the OpenLink OSDB REST API require authentication?
The specification declares no security scheme, so the operations are not gated by a declared credential. It does expose login and logout operations for establishing a session, and through Jentic your agent calls the operations directly.
How does an agent run an action safely?
It reads the action definition with GET /api/v1/actions/{serviceId}/{actionId} first, then executes it with POST /api/v1/actions/{serviceId}/{actionId}/exec. Reading the shape before calling keeps the request well-formed.
Is there an MCP server for the OpenLink OSDB REST API?
You do not need a separate MCP server to use the OpenLink OSDB REST API with an agent. Through Jentic One, the self-hosted execution layer, your agent calls the operations directly after you import them from the API Directory. Install Jentic One from github.com/jentic/jentic-one to run it yourself.
How does my agent discover OSDB operations through Jentic?
Agents search Jentic by intent, such as 'list the services on the server', and Jentic returns the matching operation with its input schema. The agent then calls the right endpoint without reading the full reference.
Can I limit what my agent is allowed to do with the OpenLink OSDB REST API?
Yes. Because you run Jentic One yourself, you decide which OSDB operations the agent may call. You can allow only the discovery operations that list and describe services and actions, and leave execute, load, and unload out of the allowed set unless you add them, so the agent acts only within the operations you permit.
Know of an official OpenAPI document? Contribute it →
For Agents
Discover OSDB services and actions, read their parameters, and execute actions through the OpenLink service layer.
Use for: List the services on the OSDB server, Load a service so its actions become available, List the actions a service defines, Read the parameters for a specific action
Not supported: Does not define the services or their business logic. Use it to discover services and actions, read their parameters and help, and execute actions on an OSDB server.
The OpenLink OSDB REST API exposes services and the actions they define so a caller can discover what is loadable, load or unload a service, list its actions, read the help for one, and execute it. An agent can walk from a list of services to a specific action's parameters and then run it, which makes it a thin orchestration layer over server-side capabilities. It also has login and logout operations for establishing a session. It suits automation that drives OSDB service actions on demand.