Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SQL Server MCP list tables in AdventureWorks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A read-only MCP (Model Context Protocol) server for SQL Server database introspection. Use with Claude Desktop to let Claude explore and query your SQL Server databases.
List databases, tables, views, stored procedures, and functions
Get object definitions (DDL/source code)
Execute read-only SELECT queries
Search for objects across databases
Read-only by design - all mutation queries are blocked
Related MCP server: mssql-mcp
# Clone the repo
git clone https://github.com/millelog/sql-server-mcp.git
cd sql-server-mcp
# Install in a virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
pip install -e .Add to your Claude Desktop config file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"sql-server": {
"command": "python",
"args": ["-m", "sql_server_mcp"],
"cwd": "C:\\path\\to\\sql-server-mcp",
"env": {
"MSSQL_HOST": "your-server",
"MSSQL_USER": "your-username",
"MSSQL_PASSWORD": "your-password",
"MSSQL_DATABASE": "master"
}
}
}
}Restart Claude Desktop after updating the config.
Variable | Description | Default |
| SQL Server hostname |
|
| SQL Server port |
|
| Username | - |
| Password | - |
| Default database |
|
| Full connection string (overrides above) | - |
| Maximum rows returned |
|
| Query timeout (seconds) |
|
| Comma-separated allowlist | - |
| Comma-separated blocklist | - |
Tool | Description |
| List all accessible databases |
| List tables in a database |
| Get CREATE TABLE DDL |
| Get column metadata |
| Get index information |
| Get foreign key relationships |
| List views in a database |
| Get CREATE VIEW DDL |
| List stored procedures |
| Get CREATE PROCEDURE DDL |
| Get procedure parameters |
| List user-defined functions |
| Get CREATE FUNCTION DDL |
| Run read-only SELECT queries |
| Get sample rows from a table |
| Search for objects by name |
| Search within object definitions |
| Get database schema summary (object counts, size) |
# Run tests
pytest tests/ -v
# Run with coverage
pytest tests/ --cov=src/sql_server_mcpMIT
Execute a read-only SELECT query
Inputs: query (required), database, max_rows.
Get the CREATE FUNCTION definition
Inputs: function (required), database.
Get the CREATE PROCEDURE definition
Inputs: procedure (required), database.
Get parameter information for a stored procedure
Inputs: procedure (required), database.
Get sample rows from a table
Inputs: table (required), database, rows, random.
Get an overview of a database schema (counts of objects, size info)
Inputs: database.
Get detailed column information for a table
Inputs: table (required), database.
Get the full CREATE TABLE definition for a table
Inputs: table (required), database.
Get index information for a table
Inputs: table (required), database.
Get foreign key relationships for a table
Inputs: table (required), database.
Get column information for a view
Inputs: view (required), database.
Get the CREATE VIEW definition
Inputs: view (required), database.
List all accessible databases on the SQL Server
Inputs: include_system, name_pattern.
List all user-defined functions in a database
Inputs: database, schema, function_type.
List all stored procedures in a database
Inputs: database, schema, name_pattern, include_system.
List all schemas in a database with object counts
Inputs: database.
List all tables in a database
Inputs: database, schema, name_pattern.
List all views in a database
Inputs: database, schema, name_pattern.
Search within object definitions (procedure/function/view source code)
Inputs: pattern (required), database, object_types.
Search for database objects by name across all databases
Inputs: pattern (required), object_types, database.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 20 tools
Every tool targets a distinct resource and action, such as listing vs. getting definitions, columns, or relationships. No two tools have overlapping purposes; even similar operations like get_table_definition vs get_table_columns are clearly separated by what they return.
All tool names follow a consistent verb_noun pattern using snake_case, with verbs like execute, get, list, and search. The naming is predictable and uniform across the entire set.
20 tools is well-scoped for a SQL Server schema exploration and querying server. Each tool covers a specific need without redundancy, and the count is appropriate for the domain's complexity.
The tool set provides comprehensive coverage for read-only database operations: listing objects, retrieving definitions, columns, indexes, relationships, sample data, and executing queries. It also includes search capabilities. There are no obvious gaps for the intended read-only scope.
Hosted SQL Server MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Draxlr's remote MCP server connects AI assistants to your SQL databases and dashboards. Explore schemas, run read-only queries, manage saved queries and dashboards, and export results, all with row-level security so each user sees only their own data.
