Data & Storage · Integration
Strongbox
Add Strongbox to your product for your customers, and give your AI agents governed access to it.
Strongbox, built by Finagraph, exists to get a business's accounting data to a lender without an exchange of PDFs: the borrower connects their own accounting system, QuickBooks, Xero or Sage among them, and what comes back is a normalised set of financial statements, transaction-level cash flow, ratios and trends, plus data-quality checks that flag missing or questionable figures before an underwriter relies on them. For an embedded integration the important detail is whose data is being read. The lender using your product initiates the request, the borrower authorises their own books, and the mapping from their chart of accounts onto a standard statement layout is configuration per engagement rather than a schema you can fix in code. fastn keeps each connection scoped to its tenant and follows the API wherever it goes.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a lender using your product request accounting data from a borrower, who connects their own books rather than emailing exports.
Read normalised statements and ratios so underwriting works from one layout no matter which accounting system the borrower runs.
Surface the data-quality checks beside the figures, so an analyst sees what is missing before they lend against it.
Re-pull on a schedule for loan monitoring, so a covenant is measured against current books rather than the ones at origination.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent summarises a borrower's cash flow trend and names the months that moved it.
An agent flags which quality checks failed on a submission and what an analyst should ask for.
An agent compares this pull with the previous one for the same borrower, with every read logged per tenant.
Example prompt
Summarise this borrower's last twelve months of cash flow and tell me which quality checks did not pass.
Set up Strongbox in 4 steps
- 01Enable the Strongbox connector in your fastn dashboard.
- 02Connect each lender's own Strongbox credentials, and let each borrower authorise their own accounting system when a request goes out.
- 03Map the statement, ratio and cash-flow fields your product reads, and decide how a failed quality check is surfaced.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Strongbox integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Strongbox integration without building it. Your customers connect their own Strongbox 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 Strongbox update is not your on-call problem.
- One integration serves your product and your agents. The same governed Strongbox 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
Works well with
QuickBooks
Xero
Sage IntacctOften used alongside
Tools the same teams tend to run next to Strongbox, across other categories.
Anthropic Claude
OpenAI
Azure OpenAI
Hugging FaceStrongbox integration FAQ
How do I add a Strongbox integration to my product?
Enable the Strongbox connector in your fastn dashboard, then let each customer authenticate their own Strongbox account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Strongbox client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Strongbox account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Strongbox 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 Strongbox 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 summarises a borrower's cash flow trend and names the months that moved it.
Who maintains the Strongbox integration?
fastn does. When Strongbox 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 Strongbox 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 Strongbox 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 Strongbox integration?
A common starting point: let a lender using your product request accounting data from a borrower, who connects their own books rather than emailing exports. 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 Strongbox integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Strongbox does not change your per-connector cost. You can start free with 3 connected accounts.
Add Strongbox to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.