Connect SQL Server to any AI.

Ask Claude or ChatGPT about the data in SQL Server or Azure SQL, limited to the tables you approve, with writes only where you allow them.

Read from SQL Server when someone asks. Nothing exported, nothing copied, and changes only where you allow them.

SQL Server connects to FrontierOps once, and any AI your team uses, such as Claude, ChatGPT, Grok or Perplexity, reaches it through that connection.
  1. SQL Server Data & warehouses
  2. FrontierOps Permissions, definitions, record
  3. Any AI The AI your team uses
Examples

Ask in any language. Answered from SQL Server.

What it can do

What the AI can read in SQL Server, and what it can do.

It can read

Read-only by default
  • Any table or view you approve in the connected database, through read-only SELECT and WITH queries
  • No reach beyond that database: USE, four-part names and linked-server functions such as OPENQUERY are blocked
  • No schema probing: INFORMATION_SCHEMA, sys views and sp_help style procedures are blocked
  • One statement per call, no GO batches, results capped by row count and size, with a timeout

It can do, if you allow it

Needs write access
  • Insert rows into an approved table
  • Update rows in an approved table, with a WHERE clause
  • Delete rows from an approved table, with a WHERE clause
  • Merge: insert or update rows in one statement, with source and target both approved

Each is its own permission, never on the User role. Stored procedures, schema changes, SET and explicit transactions are refused: every call is one auto-committed statement. Every write is on record.

Already on dbt? We import the project (dbt Core is enough), and its definitions guide every answer from SQL Server.

Why connect it

How the SQL Server integration works.

Years of operational data sit in SQL Server, often behind an ERP or an in-house app, and getting a report out of it means a ticket to IT. Connected once, your team asks in plain English and gets answers from the tables you approved, inside that one database and nothing else on the server.

Questions

What people ask about connecting SQL Server.

Does it work with Azure SQL?

Yes, with SQL authentication: a username and password. Windows (NTLM) and Microsoft Entra ID authentication are not supported.

Can it run stored procedures?

No. EXEC, xp_ and sp_ procedures, schema changes and explicit transactions are refused in every call. Reads are single SELECT or WITH statements; writes, if you turn them on, are single INSERT, UPDATE, DELETE or MERGE statements on approved tables.

Can it see other databases on the server?

No. The connected database is its whole world: USE, four-part names and linked-server functions are blocked in every query. Inside that database it sees only the tables you approve.

Is this a SQL Server MCP server?

Yes, and one built for a whole company. FrontierOps gives Claude, ChatGPT and any other MCP client one connection to SQL Server, set up once by an admin. What each role can read or change is decided in FrontierOps, and every call is on record, instead of each person running their own server with their own login.

Why not connect SQL Server to Claude or ChatGPT directly?

A direct connection links one AI to SQL Server through one person’s login, with that person’s settings. That works for one person. For a team it means no shared definitions, no single place to decide who can see or change what, and starting over when you switch AI. Through FrontierOps, SQL Server is connected once, for every AI and every agent, under one set of permissions, with every call on record.

Works well with

One connection each. One set of rules across all of them.

See every integration

Bring one question about SQL Server. We’ll connect it with you.