Data & Storage · Integration
Redox Engine
Add Redox Engine to your product for your customers, and give your AI agents governed access to it.
Redox sits between a digital health product and the systems it has to talk to, translating between FHIR R4 resources, HL7v2 messages and CCDA documents so you write to one interface rather than to every hospital separately. What you actually work with is the connection: a source, a destination and the data models or FHIR resources that flow across it, plus a sandbox environment for proving a change before a live connection is involved. The honest caveat is that the standard is not the whole story. Which fields arrive depends on how the organisation on the far side is configured, so mapping belongs per connection and per customer rather than in your code. Access is scoped per tenant, credentials are encrypted and every read and write is logged.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own Redox organisation so your product reaches the systems they are already live with, one connection at a time.
Send and receive through a destination rather than against a system directly, so adding another site is configuration rather than a release.
Work in FHIR R4 resources or in Redox data models, whichever the connection on the other end actually supports.
Prove a change against the sandbox environment first, so an integration change is not tested in production.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent reads back through a connection within scoped permissions, with every request logged and attributable.
An agent reports which destinations a customer has configured and which are currently receiving traffic.
An agent writes to a destination only where permitted, with the write attributed to the tenant that authorised it.
Example prompt
Which connections exchanged data today, and were any messages rejected on the way through?
Set up Redox Engine in 4 steps
- 01Enable the Redox Engine connector in your fastn dashboard.
- 02Have each customer connect their own Redox organisation with credentials scoped to the destinations they authorise.
- 03Map the data models or FHIR resources and the fields each connection actually carries, per customer.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Redox Engine integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Redox Engine integration without building it. Your customers connect their own Redox Engine 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 Redox Engine update is not your on-call problem.
- One integration serves your product and your agents. The same governed Redox Engine 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 Redox Engine, across other categories.
Anthropic Claude
OpenAI
Azure OpenAI
Hugging FaceRedox Engine integration FAQ
How do I add a Redox Engine integration to my product?
Enable the Redox Engine connector in your fastn dashboard, then let each customer authenticate their own Redox Engine account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Redox Engine client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Redox Engine account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Redox Engine 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 Redox Engine 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 reads back through a connection within scoped permissions, with every request logged and attributable.
Who maintains the Redox Engine integration?
fastn does. When Redox Engine 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 Redox Engine 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 Redox Engine 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 Redox Engine integration?
A common starting point: let each customer connect their own Redox organisation so your product reaches the systems they are already live with, one connection at a time. 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 Redox Engine integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Redox Engine does not change your per-connector cost. You can start free with 3 connected accounts.
Add Redox Engine to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.