Integration · Databases
AI agents for Microsoft SQL Server
Read and query Microsoft SQL Server or Azure SQL Database directly, over an encrypted connection.
- Actions
- 5
- Read
- 4
- Write
- 1
Actions
What your agents can do in Microsoft SQL Server
Read and query Microsoft SQL Server or Azure SQL Database directly, over an encrypted connection. Lists tables, describes their columns and keys, pages through rows and runs read-only SQL; writes only when the connection allows them.
Read 4
Look things up. Nothing changes.
List tables
Lists the tables and views this user can see, with their schema and an estimated row count, 200 at a time by schema then name.
Describe a table
One table's or view's columns (name, type, nullable, default), primary key, foreign keys and indexes.
Read rows
A page of a table's rows (up to 1,000), ordered by a column or by the primary key.
Run a read query
Runs one read-only SQL statement (SELECT, WITH, SHOW, EXPLAIN) and returns up to max_rows rows (default 200, at most 1,000 and about 190 KB; very large values are cut to a preview and cut says so).
Write 1
Create, change or send.
Run a write statementDeletes data
Runs one statement that changes data (INSERT, UPDATE, DELETE, MERGE) with values in params (%s placeholders (write %% for a literal %)) and returns the rows affected.
A person can approve first
Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything. Actions that delete data ask first by default.
Connection
How it connects
Connect it once in the console, then give it to the agents and workflows that need it.
Connect straight to your Microsoft SQL Server database with its address and a database user, directly or through an SSH tunnel.
Settings
- Host
- Database
Kept safe
- Credentials are stored encrypted with your organization's own keys.
- They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
- Calls go only to the tool's own servers.
Ideas
Ideas to start with
Starting points made only from the actions above. Mix them with any other tool your agents can use.
- 01
Ask about your Microsoft SQL Server data
Ask a question in plain words. The agent can list tables, describe a table or read rows in Microsoft SQL Server, then answers with what it found.
- 02
Let an agent update Microsoft SQL Server
Have the agent run a write statement in Microsoft SQL Server as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Share what it finds in Slack
Give one agent Microsoft SQL Server and Slack: it can list tables in Microsoft SQL Server and post a summary to a Slack channel in the same run.
FAQ
Microsoft SQL Server and MyDeepAgents
Can MyDeepAgents connect to Microsoft SQL Server?
Yes. The Microsoft SQL Server connector has 5 actions: 4 read and 1 makes changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Microsoft SQL Server?
Connect straight to your Microsoft SQL Server database with its address and a database user, directly or through an SSH tunnel. The connection also asks for: Host and Database. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.
Can an agent change data in Microsoft SQL Server without asking?
Only if you let it. Its one action that changes data can delete data, so it asks a person first by default.
Can I use Microsoft SQL Server in workflows as well as agents?
Yes. Every Microsoft SQL Server action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Microsoft SQL Server to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.