SQL Server MCP Server (Python)

A Model Context Protocol (MCP) server in Python for integration with Microsoft SQL Server databases.

The server provides complete schema inspection tools and CRUD (Create, Read, Update, Delete) operations, as well as MCP resources for quick data and schema queries.

Available Tools

Schema & Inspection

• list_schemas(): Lists all user schemas present in the database.

• list_tables(schema_name=None): Lists database tables and views with the option to filter by schema.

• get_table_schema(table_name, schema_name="dbo"): Returns structural details of the table (columns, data types, primary keys, foreign keys, and identities).

• get_database_schema(schema_name=None, table_name=None): Returns the complete database schema or a filtered one.

CRUD Operations

• read_records(table_name, schema_name="dbo", columns=None, where_clause=None, params=None, order_by=None, limit=100, offset=0): Queries records from a table with custom columns, parameterized WHERE filters, ordering, and pagination.

• read_query(sql_query, params=None): Executes a custom SELECT query in T-SQL with support for positional parameters (?).

• insert_record(table_name, data, schema_name="dbo"): Inserts a single record (key/value dictionary) into a table.

• bulk_insert_records(table_name, records, schema_name="dbo"): Inserts multiple records in batch within a transaction.

• update_records(table_name, data, where_clause, where_params=None, schema_name="dbo"): Updates records matching a parameterized WHERE clause.

• delete_records(table_name, where_clause, params=None, schema_name="dbo"): Safely removes records matching a WHERE clause.

• execute_sql(sql_statement, params=None): Executes arbitrary DDL/DML commands (CREATE, ALTER, DROP, INSERT, UPDATE, DELETE).

Related MCP server: SQL Server MCP

MCP Resources

• sqlserver://schema: Returns the complete database schema in JSON format.

• sqlserver://tables: Returns the list of available tables and views.

Installation and Configuration

1. Requirements

• Python >= 3.10

• SQL Server Driver (Supports pyodbc with SQL Server ODBC Driver and pymssql for pure Python connections).

2. Environment Configuration (.env)

Create a .env file in the project root or define the environment variables:

SQLSERVER_HOST=localhost
SQLSERVER_PORT=1433
SQLSERVER_DATABASE=MeuBanco
SQLSERVER_USER=sa
SQLSERVER_PASSWORD=SuaSenha123!
SQLSERVER_DRIVER_TYPE=auto
SQLSERVER_TRUST_SERVER_CERTIFICATE=true

3. Installation

python -m venv .venv
# Windows
.\.venv\Scripts\activate
# Linux/macOS
source .venv/bin/activate

pip install -e .

Configuration in MCP Clients

Example of mcp.json / Client Configuration

{
  "mcpServers": {
    "sql-server": {
      "command": "python",
      "args": [
        "-m",
        "sql_server_mcp.server"
      ],
      "env": {
        "SQLSERVER_HOST": "localhost",
        "SQLSERVER_PORT": "1433",
        "SQLSERVER_DATABASE": "MeuBanco",
        "SQLSERVER_USER": "sa",
        "SQLSERVER_PASSWORD": "SuaSenha123!",
        "SQLSERVER_TRUST_SERVER_CERTIFICATE": "true"
      }
    }
  }
}

🐳 Docker & Makefile

You can use the Makefile to facilitate building and running via Docker:

# Compilar a imagem Docker
make build

# Executar o servidor MCP em container utilizando as variáveis do .env
make run

# Rodar os testes unitários dentro do container Docker
make docker-test

# Exibir ajuda dos comandos Makefile
make help

🧪 Tests

To run the application's unit tests:

pytest