For Agents
Programmatically [user][data sources][authorizers], [user][data sources][authorized]. Covers 20 operations with basic authentication.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ROOK, 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%2Frook-connect.com%2Frook-connect" | 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%2Frook-connect.com%2Frook-connect" | 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 ROOK API.
[User][Data Sources][Authorizers]
[User][Info]
[Physical][Summary]
[Physical][Events][Activity]
GET STARTED
Use for: I need to [user][data sources][authorizers], I want to [user][data sources][authorized], Search for [user][info], Find all [user][data sources][revoke]
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
Intro [ROOK](https://docs.tryrook.io/docs/Definitions#rook) is a set of services that simplifies the collection, processing, and delivering of [Users'](https://docs.tryrook.io/docs/Definitions#User) [HealthData](https://docs.tryrook.io/docs/Definitions#health-data) from various data sources. Testing You can use the following constants to test the API and receive default responses: - client_uuid = . The API exposes 20 endpoints secured with basic authentication.
[Physical][Events][Heart Rate]
Patterns agents use ROOK API for, with concrete tasks.
★ Developer Tools Operations
Use the ROOK to perform developer tools operations programmatically. The API provides 20 endpoints covering core functionality including [user][data sources][authorizers], [user][data sources][authorized], [user][info].
Call GET /api/v1/client_uuid/{client_uuid}/user_id/{user_id}/data_sources/authorizers to [user][data sources][authorizers]
Automated Health Management
Automate health operations by combining multiple ROOK endpoints. Agents can [user][data sources][authorized] and then [user][info] in a single workflow.
Call GET /api/v1/user_id/{user_id}/data_sources/authorized to [user][data sources][authorized], then verify the result
AI Agent Integration via Jentic
AI agents discover and call ROOK endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle basic tokens manually.
Search Jentic for '[user][data sources][authorizers]', load the operation schema, and execute with Jentic-managed credentials
20 endpoints — intro [rook](https://docs.
METHOD
PATH
DESCRIPTION
/api/v1/client_uuid/{client_uuid}/user_id/{user_id}/data_sources/authorizers
[User][Data Sources][Authorizers]
/api/v1/user_id/{user_id}/data_sources/authorized
[User][Data Sources][Authorized]
/v2/processed_data/user/info
[User][Info]
/api/v1/user_id/{user_id}/data_sources/revoke_auth
[User][Data Sources][Revoke]
/v2/processed_data/physical_health/summary
[Physical][Summary]
/v2/processed_data/physical_health/events/activity
[Physical][Events][Activity]
/v2/processed_data/physical_health/events/heart_rate
[Physical][Events][Heart Rate]
/v2/processed_data/physical_health/events/oxygenation
[Physical][Events][Oxygenation]
/api/v1/client_uuid/{client_uuid}/user_id/{user_id}/data_sources/authorizers
[User][Data Sources][Authorizers]
/api/v1/user_id/{user_id}/data_sources/authorized
[User][Data Sources][Authorized]
/v2/processed_data/user/info
[User][Info]
/api/v1/user_id/{user_id}/data_sources/revoke_auth
[User][Data Sources][Revoke]
/v2/processed_data/physical_health/summary
[Physical][Summary]
What agents get from Jentic-routed access to this vendor.
Setup
Wiring ROOK by hand means implementing its HTTP basic auth and sending it on every request and handling the request plumbing yourself. Through Jentic you install once, import ROOK from the API Directory, store the basic credentials once, and your agent calls it.
Permission scoping
ROOK puts the client and user ids in the URL path (/client_uuid/{client_uuid}/user_id/{user_id}/...), so a rule can pin your agent to one user's data. You choose the operations it may call, so ones like revoking a data-source authorization are not included unless you add them.
Credential isolation
Your ROOK basic credentials 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.
Intent-based discovery
Agents search Jentic by intent such as 'list a user's authorized data sources' or 'get a physical health summary', and Jentic returns the matching ROOK operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Github
Alternative developer tools API
Choose Github when you need a different approach to developer tools operations
Specific to using ROOK API through Jentic.
What authentication does the ROOK use?
The ROOK uses HTTP Basic authentication with username and password. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I [user][data sources][authorizers] with the ROOK?
Yes. Use the GET /api/v1/client_uuid/{client_uuid}/user_id/{user_id}/data_sources/authorizers endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the ROOK?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I [user][data sources][authorizers] through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for '[user][data sources][authorizers]'. Jentic returns the matching ROOK operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the ROOK have?
The ROOK exposes 20 endpoints covering health, user, physicalhealthsummary operations.
/v2/processed_data/physical_health/events/activity
[Physical][Events][Activity]
/v2/processed_data/physical_health/events/heart_rate
[Physical][Events][Heart Rate]
/v2/processed_data/physical_health/events/oxygenation
[Physical][Events][Oxygenation]