Data & Storage · Integration
PatientSource
Add PatientSource to your product for your customers, and give your AI agents governed access to it.
Embed a PatientSource integration so your product can work with the records a hospital or clinic already keeps in their own system rather than asking them to copy data somewhere else. PatientSource is a modular electronic patient record built to sit alongside the systems a site already runs, so what any given deployment exposes depends on which modules that site has configured. Field and record mapping is therefore configuration per customer rather than code, and every deployment is treated as its own tenant. Health data carries stricter access rules than most systems, so each customer connects their own deployment, access is limited to the fields you map, credentials are encrypted and every read and write is logged. fastn owns the credential handling, retries, pagination and API upkeep, and the same governed connection is what your AI agents use.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own PatientSource deployment so your product reads and writes their records with no per-customer code.
Read only the fields you have mapped, so your product exposes what it genuinely needs rather than a whole record.
Write output your product generates back into the customer's own system so staff are not working from a second copy.
Support deployments that differ module by module as per-tenant configuration rather than a branch in your code.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent retrieves a specific record within scoped permissions, with every read logged and attributable.
An agent files a document your workflow produced back into the customer's own deployment, with the write attributed.
An agent answers an administrative question from that tenant's own records rather than a stale export.
Example prompt
Find the records updated in the last 24 hours and list the ones still missing required information.
Set up PatientSource in 4 steps
- 01Enable the PatientSource connector in your fastn dashboard.
- 02Have each customer connect their own deployment with credentials scoped to the records you use.
- 03Map the records and fields your product needs, and only those, per customer.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the PatientSource integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a PatientSource integration without building it. Your customers connect their own PatientSource account inside your product and work their records, datasets and fields there, with no per-customer code on your side.
- Handle the part that actually costs time: schemas differ per customer and change without notice, and volumes can be large. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a PatientSource update is not your on-call problem.
- One integration serves your product and your agents. The same governed PatientSource connection powers in-product features and gives AI agents scoped, audited access, so you read and write your customers' data where it already lives without wiring it twice.
Used by these teams
Compare with
Epic
Oracle Health
FHIROften used alongside
Tools the same teams tend to run next to PatientSource, across other categories.
Anthropic Claude
OpenAI
Azure OpenAI
Hugging FacePatientSource integration FAQ
How do I add a PatientSource integration to my product?
Enable the PatientSource connector in your fastn dashboard, then let each customer authenticate their own PatientSource account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no PatientSource client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own PatientSource account?
Yes. Every connection is scoped to the individual customer, so each authorises their own PatientSource account and only ever sees their own records, datasets and fields. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this PatientSource integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent retrieves a specific record within scoped permissions, with every read logged and attributable.
Who maintains the PatientSource integration?
fastn does. When PatientSource changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Does the PatientSource integration adapt when a customer's schema changes?
Schema and field mapping is configuration per customer, so a change on their side is a mapping update rather than a code change and a release on yours.
How are large PatientSource reads handled?
Pagination and throttling are handled for you, and initial backfills are rate-limited so a large import does not exhaust a customer's API allowance.
What can I build with the PatientSource integration?
A common starting point: let each customer connect their own PatientSource deployment so your product reads and writes their records with no per-customer code. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the PatientSource integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding PatientSource does not change your per-connector cost. You can start free with 3 connected accounts.
Add PatientSource to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.