For Agents
Oyster uses OAuth2 to enable customers to grant access to their data to third party applications. Customers also need to use this API to authenticate themselves when making API requests.
Use for: I need to access Endpoints, How do I use the oysterhr.com API?, Get data from oysterhr.com
Not supported: Provides access to Endpoints functionality as defined in the OpenAPI specification.
Oyster uses OAuth2 to enable customers to grant access to their data to third party applications. Customers also need to use this API to authenticate themselves when making API requests.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Endpoints, 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%2Foysterhr.com%2Foysterhr" | 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%2Foysterhr.com%2Foysterhr" | 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 Endpoints API.
Create an access token
Approve expense
Decline expense
Retrieve an individual expense
GET STARTED
Create expense
Patterns agents use Endpoints API for, with concrete tasks.
★ Basic Endpoints Integration
Integrate Endpoints into your application to access its core functionality.
Use the Endpoints API to access vendor services and data.
17 endpoints — oyster uses oauth2 to enable customers to grant access to their data to third party applications.
METHOD
PATH
DESCRIPTION
/oauth2/token
Create an access token
/v1/expenses/{id}/approve
Approve expense
/v1/expenses/{id}/decline
Decline expense
/v1/expenses/{id}
Retrieve an individual expense
/v1/expenses
Create expense
/v1/company
Retrieve company details
/v1/departments
Retrieve all departments
/oauth2/token
Create an access token
/v1/expenses/{id}/approve
Approve expense
/v1/expenses/{id}/decline
Decline expense
/v1/expenses/{id}
Retrieve an individual expense
/v1/expenses
Create expense
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Oyster HR API by hand means minting a bearer token through /oauth2/token and carrying it on every expense, company, and department call. Through Jentic you install once, import the Oyster HR API from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Oyster HR puts the expense id in the URL path (/v1/expenses/{id}), so a rule can pin your agent to one expense for the reads and actions you allow. You choose the operations it may call, so approving or declining an expense is not included unless you add it.
Credential isolation
Your Oyster HR bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create an expense' or 'list departments', and Jentic returns the matching Oyster HR operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Specific to using Endpoints API through Jentic.
What authentication does the Endpoints use?
The Endpoints uses bearer authentication.
How many endpoints does the Endpoints have?
The Endpoints has 17 endpoints available.
Can I limit what my agent is allowed to do with the Oyster HR API?
Yes. Because you run Jentic One yourself, your own rules decide which Oyster HR operations and credentials the agent may use. Oyster HR puts the expense id in the URL path, such as /v1/expenses/{id}, so you can pin the agent to a single expense for the reads and actions you allow. You choose the operations it can call, so approving or declining an expense is excluded unless you explicitly add those endpoints.
/v1/company
Retrieve company details
/v1/departments
Retrieve all departments