MCP Server

SQL Server MCP server

Run a governed MCP server in front of SQL Server so an AI agent can read it without holding your credentials. The agent sees only the tables and columns you allow. Schema-qualified tables with SQL Server types mapped to something an agent can reason about — UNIQUEIDENTIFIER, DATETIMEOFFSET, NVARCHAR(MAX).

Start freeHow Agent Gateway works

What to check before an agent reads SQL Server

Specific to this engine, not to MCP. Each one changes what a scoped token can reach.

Allowlists must be schema-qualified

dbo.customers and staging.customers are different tables with the same name. An allowlist entry that ignores the schema is ambiguous at best, and the staging copy is often the one nobody masked.

An untrusted foreign key was never validated

Constraints re-enabled after a bulk load without WITH CHECK are marked is_not_trusted. The relationship exists on paper; the rows under it were never checked against it, so a join an agent follows may not mean what it appears to.

NVARCHAR(MAX) is an unbounded text field

Notes and description columns of this type routinely accumulate personal data that no column name would suggest. Worth denying or projecting through a view rather than assuming.

Connecting an agent to SQL Server

Any MCP client works — the endpoint is the same, only the client's config file differs.

{
  "mcpServers": {
    "dbshifts": {
      "url": "https://dbshifts.com/api/v1/agent-gateways/mcp",
      "headers": { "Authorization": "Bearer agt_your_token_here" }
    }
  }
}
Claude Desktop setup →Cursor setup →Windsurf setup →Cline (VS Code) setup →a custom agent (LangChain, LlamaIndex, or your own) setup →

How it works

01

Register the database

Connect it once with read-only credentials. The schema is introspected and scanned for PII automatically — you see what's sensitive before anything is exposed.

02

Set the policy

Pick the tables and columns agents may read. Set PII masking, a row cap, a rate limit, and daily/monthly usage budgets. Default is deny.

03

Issue a scoped token

One agt_ token per agent, revocable independently, optionally IP-bound and time-windowed. Never your database password.

04

Point the agent at it

Drop the endpoint and token into your client's MCP config. Every call is policy-checked, masked, capped and logged.

Tools the agent gets

Exactly the 26 tools the MCP server exposes — no raw SQL is accepted from the agent on any of them. What each one does.

Readlist_tables, query_table, list_views, query_view, aggregate_table, query_related
Retrievallist_search_indexes, search
Metricslist_metrics, query_metric
Background jobssubmit_job, get_job, list_jobs, cancel_job
Change feedslist_feeds, subscribe_changes, poll_changes, unsubscribe_changes
Historylist_history, diff_history, query_at_commit
Access requestsrequest_access, list_access_requests
Writes (human-approved)list_actions, propose_action, propose_action_plan

Frequently asked questions

Do I have to give the AI agent my SQL Server password?

No — that's the entire point. The agent authenticates with a scoped agt_ token issued by the gateway. The database credentials stay on the server and are never sent to the agent, the model provider, or the client machine. Revoke a token and that agent loses access immediately, without touching any other agent or rotating your database password.

Can the agent read columns I haven't allowed?

No. The policy is default-deny: an agent sees only the tables and columns you explicitly allow. Denied columns are not returned, and PII columns are masked server-side before results ever leave the gateway — including inside aggregates, so a masked column can't be grouped or filtered back into visibility.

Can the agent modify or delete data?

Reads are read-only by construction. Writes exist only as named, parameterized actions you define in advance — the agent can propose one, but a human approves it (in-app or from Slack) before anything executes. Approved writes are audited and carry a one-click undo, plus a version-controlled history of the affected table.

What stops an agent from pulling the entire database?

Layered limits: a per-query row cap, a per-minute rate limit, and cumulative usage budgets (daily queries, daily rows, monthly rows) per token and gateway-wide. Tokens can also be IP-bound and time-windowed, so a leaked token is useless outside your network or outside working hours.

How do I see what the agent actually did?

Every call is logged: which token, which tool, which table, which columns were masked, how many rows came back, and what was denied. You can replay any logged read to see exactly what the agent saw at the time.

Set up your MCP client

PostgreSQL MCP serverMySQL MCP serverMariaDB MCP serverOracle MCP serverSQLite MCP serverMongoDB MCP server

Not connecting an agent yet? The gateway's policy sits on top of whatever the database user is allowed to do, so the read-only user underneath it is worth getting right first — the exact commands for SQL Server are on the Data Console page for it.

Ship agents without betting the database on them.

Free to start — no card. Read-only, masked, rate-limited, fully audited.

Get started