How to Configure Make SQL Server MCP Server
To set up a make sql server mcp server, connect your workflow app to a database user. You then assign read or write roles to control what queries the agent runs. Many teams start by using an admin login so their automated tasks work right away. This shortcut gives the workflow engine far too much power over production data. If a prompt goes wrong, a broad role lets the agent change or drop tables. How to set up a make sql server mcp server with native roles A safe setup starts inside the data
Your coding agents run with your access.
Claude Code reaches prod with a developer's credentials, and approval prompts get clicked through. hoop.dev checks every query, masks sensitive data, and holds risky changes for a human.
To set up a make sql server mcp server, connect your workflow app to a database user. You then assign read or write roles to control what queries the agent runs. Many teams start by using an admin login so their automated tasks work right away. This shortcut gives the workflow engine far too much power over production data. If a prompt goes wrong, a broad role lets the agent change or drop tables.
How to set up a make sql server mcp server with native roles
A safe setup starts inside the database before you build any workflow steps. In SQL Server, a database user represents the login identity when an app connects. If your automation needs many databases on one instance, use a standard login in master. If the agent only needs one database, you can use a contained database user instead. An admin must first turn on contained databases on the server and the target database. SQL Server supports thirteen different types of database users for various login needs.
After you create the user, you must assign a role that limits its power. Many teams pick fixed database roles to get the workflow running fast. Every role, including the default public role, holds the basic permission to connect. You cannot change the built-in permissions that belong to fixed database roles. If the agent only needs to pull reports, add the user to the read-only role. Members of this reader role can read all data across all user tables and views. If the workflow must update records, teams often add the writer role. The writer role lets the user add, change, or delete data in all user tables. You can also assign deny roles to block reading or writing across all tables. Never assign the owner role to an automated workflow or model context tool. The owner role can run all maintenance tasks and even drop the whole database.
What native database roles solve and what they leave open
Native roles do a good job of sorting out who can log in. They also draw a hard line between reading data and writing data at the database level. A read-only user paired with a deny writer role stops accidental table edits. This setup protects your core records from bad update or delete commands.
Still, fixed roles apply to every single user table and view at once. A reader role lets the workflow pull every column from every table in that database by default. When an AI agent runs a query, it might pull emails or phone numbers. It can also pull credit card numbers or national IDs stored in customer tables. Native roles decide who logs in, not what individual statements do in flight. They do not rewrite sensitive fields in query results before the data leaves the server. Also, sharing one static database password across many workflows makes auditing very hard. When five workflows share one login, the server logs show the same user for all queries. You cannot tell which specific workflow step or user triggered a risky query.
Kubernetes API Server Access + End-to-End Encryption: architecture patterns and best practices
Continue reading? Get the full guide.
Free. No spam. Unsubscribe anytime.
Why query-level controls matter for automated workflows
Modern automation tools run fast and build queries based on changing inputs. Static roles at the database level are too blunt for this type of traffic. Teams need a way to inspect each command right when the agent sends it. Instead of granting access to all tables, you want rules that check the active query. Data masking can rewrite matched fields like emails and card numbers in the results. That way, the workflow gets the rows it needs without exposing raw private data.
Check SQL Server batches and results on the wire
SQL Server logins and roles decide who connects. They do not check what each TDS batch does or mask sensitive values in returned rows. With hoop.dev, you run an open-source proxy, a sidecar for your SQL Server. It reads plain batches and parameterized queries on the TDS wire while passing Windows login through untouched.
Before a batch hits the server, hoop.dev guardrails check the statement against your rules. Disallowed actions get a native TDS error with your message. On the way back, hoop.dev data masking rewrites sensitive values in supported result columns that match your rules. Every query and decision is logged. Explore the MIT-licensed project on GitHub.
Frequently asked questions
What database role should a read-only workflow use?
Assign the built-in reader role so the user can read user tables and views. You can also add the deny writer role to block any data changes.
Should I use a standard login or a contained user for automation?
Use a contained user if the workflow only needs one or a few databases. Use a login tied to master if the agent needs many databases on the instance.
Why is the built-in reader role still risky for AI agents?
The reader role allows reading all data from all user tables and views. It does not mask emails, phone numbers, or card numbers in the query results.
Related guides
In this post