Data & Storage · Integration
Microsoft SQL Server
Add Microsoft SQL Server to your product for your customers, and give your AI agents governed access to it.
SQL Server is where a lot of your customers' operational data actually sits, often in a database an in-house team has owned for a decade, so an embedded Microsoft SQL Server integration means reading and writing it in place instead of asking for a nightly extract. The surface is T-SQL: tables, views, and the stored procedures that frequently hold business rules nobody wants reimplemented in your app. Three facts shape the build, and none of them look like an OAuth connector. Authentication belongs to the connection rather than to an app, so it is SQL authentication, Windows authentication or Microsoft Entra ID depending on how that instance is run. Deployment differs, because a managed Azure SQL database does not offer everything a self-managed instance does, and habits like linked servers and cross-database queries belong to the latter. And reachability is a network question, since an on-premise instance sits behind a firewall on a port somebody opens deliberately.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Have each customer supply their own SQL Server host and login, instead of shipping a connection string you chose.
Call the stored procedures a customer's DBAs already maintain, so business rules stay where they are tested.
Read and write specific tables and views, mapping their column names and types per customer instead of assuming a schema.
Treat the difference between an on-premise instance and Azure SQL as configuration, not two code paths in your product.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent runs a scoped read-only T-SQL query to ground an answer in the customer's own database, with the statement logged.
An agent inspects the columns and types of a table before it writes anything to it.
An agent executes a stored procedure it has been permitted to call, with the parameters it passed recorded.
Example prompt
Query this customer's SQL Server for orders that failed validation overnight and tell me which column each one tripped on.
Set up Microsoft SQL Server in 4 steps
- 01Enable the Microsoft SQL Server connector in your fastn dashboard.
- 02Have each customer supply their own host, port, database and login, plus which authentication mode that instance uses.
- 03Map the tables, views, columns and stored procedures your product touches, per customer, and decide which are writable.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Microsoft SQL Server integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Microsoft SQL Server integration without building it. Your customers connect their own Microsoft SQL Server 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 Microsoft SQL Server update is not your on-call problem.
- One integration serves your product and your agents. The same governed Microsoft SQL Server 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
MySQL
PostgreSQL
Azure Data ExplorerOften used alongside
Tools the same teams tend to run next to Microsoft SQL Server, across other categories.
Anthropic Claude
OpenAI
Azure OpenAI
Hugging FaceMicrosoft SQL Server integration FAQ
How do I add a Microsoft SQL Server integration to my product?
Enable the Microsoft SQL Server connector in your fastn dashboard, then let each customer authenticate their own Microsoft SQL Server account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Microsoft SQL Server client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Microsoft SQL Server account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Microsoft SQL Server 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 Microsoft SQL Server 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 runs a scoped read-only T-SQL query to ground an answer in the customer's own database, with the statement logged.
Who maintains the Microsoft SQL Server integration?
fastn does. When Microsoft SQL Server 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 Microsoft SQL Server 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 Microsoft SQL Server 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 Microsoft SQL Server integration?
A common starting point: have each customer supply their own SQL Server host and login, instead of shipping a connection string you chose. 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 Microsoft SQL Server integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Microsoft SQL Server does not change your per-connector cost. You can start free with 3 connected accounts.
Add Microsoft SQL Server to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.