Atlas / MCP servers / jexinsam / MSSQL

MSSQLSAFE

mcp/jexinsam/mssql-3

A Model Context Protocol (MCP) server facilitating secure interactions with MSSQL databases.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
3 1r · 2w · 0d
Transport
streamable-http
License
MIT
Stars
59
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

MSSQL MCP Server is a Model Context Protocol (MCP) server that enables secure and structured interaction with Microsoft SQL Server (MSSQL) databases. It allows AI assistants to:

  • List available tables
  • Read table contents
  • Execute SQL queries with controlled access

Built on MCP SDK v2 (2026-07-28 spec) with support for both stdio and Streamable HTTP transports.

Features

  • Secure MSSQL Database Access through environment variables
  • SQL Injection Protection with identifier validation
  • Read-Only & Write Tools with appropriate MCP annotations
  • Windows Authentication support via Trusted Connection
  • Dual Transport — stdio (default) and HTTP
  • Docker Support with pre-configured ODBC drivers
  • Comprehensive Logging for monitoring queries and operations

Installation

pip install mssql-mcp-server

Configuration

Set the following environment variables to configure database access:

# Required
MSSQL_DATABASE=your_database

# Authentication (choose one):
# Option 1: SQL Server Authentication
MSSQL_USER=your_username
MSSQL_PASSWORD=your_password

# Option 2: Windows / Kerberos Authentication
Trusted_Connection=yes

# Optional
MSSQL_HOST=localhost           # or use MSSQL_SERVER
MSSQL_DRIVER=SQL Server        # default driver
TrustServerCertificate=no      # default: no (set to yes for self-signed certs)
MCP_TRANSPORT=stdio            # or "streamable-http" for Streamable HTTP

Available Tools

Usage

With Claude Desktop

Add this configuration to `cl

Read from source at commit 53bc99848068OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mssql_mcp_server --env MSSQL_PASSWORD=${MSSQL_PASSWORD} -- uvx mssql_mcp_server
claude-desktop
{
  "mcpServers": {
    "mssql_mcp_server": {
      "command": "uvx",
      "args": [
        "mssql_mcp_server"
      ],
      "env": {
        "MSSQL_PASSWORD": "${MSSQL_PASSWORD}"
      }
    }
  }
}
03

Exposed tools (3)

1 read · 2 write · 0 destructive.

ToolRiskDescription
execute_sqlwriteExecute any SQL statement on the MSSQL server.
list_tablesreadList all available tables in the connected MSSQL database.
query_sqlwriteExecute a read-only SQL SELECT query on the MSSQL server.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (3 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (3)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements-dev.txt
pytest, pytest-cov, black, isort, mypy
Why it matters. 5 requirement(s) not pinned with ==
Fix. pin exact versions
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
mcp, pyodbc
Why it matters. 2 requirement(s) not pinned with ==
Fix. pin exact versions
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:14
- **Secure MSSQL Database Access** through environment variables
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 53bc99848068full audit observations/trust-audit/mcp-server/jexinsam__mssql-3.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0853bc99848068SAFEB89first audit
06

Questions

What is the MSSQL MCP server?

A Model Context Protocol (MCP) server facilitating secure interactions with MSSQL databases.

What tools does MSSQL expose?

3 in total: 1 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is MSSQL safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does MSSQL need?

It reads MSSQL_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does MSSQL run?

It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as mssql_mcp_server.

How current is this page?

The grade is for one exact copy of the source (53bc99848068), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement