canonical: https://jentic.com/apis/patientview.org/patientview # PatientView The PatientView API reads patient health records for the PatientView renal patient portal, so an application can retrieve a patient's basic details and their clinical observations. You log in to obtain a session token, then read a user's basic information, the observation types available for them, and their observations, including patient-entered readings. Patient management endpoints read and save diagnoses, lookup types, and surgeries for a user within a group. The API is organised around a user id that identifies whose records are being read. ## For AI agents Read a PatientView user's basic details, available observation types, and observations, and read or save patient management diagnoses and surgeries. Authenticates through a login operation that returns a session token; the spec declares no separate security scheme. ## Scope Does not handle appointment booking, messaging, or account registration. Use for reading PatientView user details, observations, and patient management records only. ## Capabilities - Log in to obtain a session token and log out to end it - Read a patient's basic details - List the observation types available for a user - Read a user's observations, including patient-entered readings - Read patient management diagnoses and lookup types - Save patient management records and surgeries for a user ## Use cases ### Agent-Driven Health Record Lookups An AI agent connected through Jentic logs in, reads a user's basic details and observations, and summarises them so a clinician can ask for a patient's recent readings in plain language. The agent reads the available observation types first, then fetches the observations for the type requested. Example prompt: Read this user's latest blood pressure observations and summarise the trend ### Observation History Retrieval An application reads a user's observations of a given type over time, including the readings the patient entered themselves, so it can chart a measurement's history. It uses the available observation headings to know which types exist for the user before requesting them. Example prompt: List the observation types for this user and return the full history for their weight readings ### Patient Management Records A workflow reads and saves patient management data such as diagnoses and surgeries for a user within a group, so a care record stays current. It reads the lookup types first to use valid codes, then saves the record. Example prompt: Read the diagnosis lookup types, then save a new diagnosis record for this user in their group ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/auth/login` | Log in | | GET | `/patient/{userId}/basic` | Get basic patient information | | GET | `/user/{userId}/observations` | Get observations for a user | | GET | `/user/{userId}/observations/{code}` | Get observations of a certain type | | GET | `/user/{userId}/availableobservationheadings` | Get available observation types for a user | | GET | `/patientmanagement/diagnoses` | Get patient management diagnoses | ## Key resources - **Users** — The patients whose records are read, identified by a user id in the path - **Observations** — Clinical readings for a user, by type, including patient-entered values - **Patient management records** — Diagnoses, lookup types, and surgeries read and saved for a user within a group - **Session** — The session token returned by login and used to identify the user on later calls ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 69 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 90 / 100 - Developer Experience & Jentic Compatibility: 63 / 100 - AI-Readiness & Agent Experience: 44 / 100 - Agent Usability: 94 / 100 - Security: 100 / 100 - AI Discoverability: 100 / 100 - **View full report:** https://jentic.com/apis/patientview.org/patientview/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the PatientView API by hand means calling its login operation to get a session token, passing that token on later calls, and mapping observations by their type codes. Through Jentic you install once, import PatientView from the API Directory, and your agent calls it. - **Permission scoping:** PatientView puts the user id in the URL path, so a rule can limit your agent to reading one user's records. You choose which operations it may call, so you can allow reading observations while leaving the save operations out, and every call it makes is logged. - **Credential handling:** PatientView authenticates through a login operation rather than a stored API key, so your agent obtains a short-lived session token at login and passes it on later calls. There is no long-lived key for Jentic to hold, and the login exchange stays inside your own instance. - **Discovery method:** Agents search Jentic by intent such as 'read a user's observations' or 'get a patient's basic details', and Jentic returns the matching PatientView operation with its input schema so the agent calls the right endpoint without reading the reference docs. ## Related APIs - **DrChrono API** — Electronic health record platform for patients, appointments, and clinical data - **openEHR API** — Open standard and API for structured, vendor-neutral clinical records ## FAQ ### Is there a PatientView MCP server? You don't need an MCP server to give your agent the PatientView API. Jentic connects it directly from the API Directory: import it and your agent can log in and read a user's records and observations straight away, with no extra server to run and no tool definitions to load into the agent's context. ### Can I limit what my agent is allowed to do with the PatientView API? Yes. Because PatientView puts the user id in the URL path, you can write a rule that limits your agent to reading one user's records. You also choose which operations it may call, so you can allow the read operations while leaving the save operations out, and every call it makes is logged. ### What authentication does the PatientView API use? The PatientView API declares no security scheme in its OpenAPI spec. Instead it exposes a login operation that returns a session token, and later calls include that token to identify the user. There is no long-lived API key to hold. ### Can I read patient-entered observations with the PatientView API? Yes. The API reads a user's observations by type, including the readings the patient entered themselves, and it lists the observation types available for that user. So an agent can retrieve both clinical and patient-entered values for a measurement. ### What are the rate limits for the PatientView API? The OpenAPI spec does not specify rate limits for the PatientView API. For current guidance, see the PatientView documentation at https://www.patientview.org. ### How do I read PatientView records through Jentic? Import the PatientView API from the Jentic API Directory, then have your agent issue a request such as 'read this user's recent observations'. Jentic matches the intent to the right operation and returns its input schema so the agent builds the correct request. To run it on your own infrastructure, install Jentic One from its GitHub repo.